# Research Agent Skills

> 281 open-source Agent Skills (SKILL.md) for academic research by Kalaris Labs: research paper and thesis writing without AI slop, journal formatting (Nature, Science, Cell, IEEE, ACM, Elsevier, Springer LNCS, PLOS, APA 7, arXiv), literature and systematic reviews (PRISMA 2020), citation verification, and 100+ scientific databases and analysis packages. Install: `npx research-agent-skills`.

## Docs

- [README](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/README.md): overview, installation for Claude Code, Codex, Cursor, Gemini CLI, Copilot
- [Documentation site](https://docs.kalarislabs.com/): guides for papers, theses, systematic reviews
- [Machine-readable catalog](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/catalog/skills.json): every skill with category and description
- [Benchmarks](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/benchmarks/README.md): how skills are evaluated

## research-writing

- [abstract-and-title](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/abstract-and-title/SKILL.md): Write and sharpen research paper titles, abstracts (structured and unstructured), keywords, highlights, significance statements, graphical-abstract text and lay summaries.
- [cover-letter-to-editor](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/cover-letter-to-editor/SKILL.md): Write journal submission cover letters, presubmission inquiries, transfer requests, and reviewer suggestion or exclusion lists that help a manuscript get past editorial triage.
- [dhdna-profiler](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/dhdna-profiler/SKILL.md): Extract cognitive patterns and thinking fingerprints from any text.
- [markdown-mermaid-writing](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/markdown-mermaid-writing/SKILL.md): Writes scientific documents and documentation as markdown with embedded Mermaid diagrams as the canonical, git-diffable source format.
- [market-research-reports](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/market-research-reports/SKILL.md): Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios.
- [ml-paper-writing](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ml-paper-writing/SKILL.md): Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM.
- [peer-review](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/peer-review/SKILL.md): Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
- [rebuttal-and-response-to-reviewers](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/rebuttal-and-response-to-reviewers/SKILL.md): 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, AC…
- [reproducibility-statement](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/reproducibility-statement/SKILL.md): 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, Nat…
- [research-grants](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/research-grants/SKILL.md): Guides writing of competitive research grant proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC.
- [scholar-evaluation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scholar-evaluation/SKILL.md): Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls.
- [scientific-critical-thinking](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-critical-thinking/SKILL.md): Evaluate scientific claims and evidence quality.
- [scientific-writing](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-writing/SKILL.md): Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency…
- [systems-paper-writing](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/systems-paper-writing/SKILL.md): Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys.
- [unslop-academic-writing](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/unslop-academic-writing/SKILL.md): Remove AI slop from research writing so papers, theses, grant proposals, reviews and rebuttals read as written by a careful human expert.

## journal-formats

- [acm-sigconf](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/acm-sigconf/SKILL.md): 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…
- [apa7](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/apa7/SKILL.md): 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 keywo…
- [arxiv-submission](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/arxiv-submission/SKILL.md): 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 lice…
- [cell-press](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/cell-press/SKILL.md): 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,…
- [elsevier-cas](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/elsevier-cas/SKILL.md): 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 singl…
- [ieee-transactions](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ieee-transactions/SKILL.md): 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, a…
- [nature-portfolio](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nature-portfolio/SKILL.md): Prepare manuscripts for Nature and Nature Portfolio journals (Nature, Nature Communications, Nature Methods, Nature Biotechnology, Scientific Reports and other Nature-branded titles), covering articl…
- [plos](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/plos/SKILL.md): 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 an…
- [science-aaas](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/science-aaas/SKILL.md): Prepare manuscripts for Science and the Science family of journals (Science, Science Advances, Science Translational Medicine, Science Robotics, Science Immunology, Science Signaling), covering Resea…
- [springer-lncs](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/springer-lncs/SKILL.md): 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 te…
- [venue-templates](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/venue-templates/SKILL.md): Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds.

## literature-review

- [bgpt-paper-search](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/bgpt-paper-search/SKILL.md): Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.
- [bibtex-hygiene](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/bibtex-hygiene/SKILL.md): Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission.
- [citation-management](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/citation-management/SKILL.md): 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…
- [citation-verification](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/citation-verification/SKILL.md): Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission.
- [exa-search](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/exa-search/SKILL.md): Web toolkit powered by Exa, tuned for scientific and technical content.
- [firecrawl-research-index](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/firecrawl-research-index/SKILL.md): Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion.
- [liteparse](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/liteparse/SKILL.md): Local document and PDF parsing that returns spatial text with bounding boxes.
- [literature-review](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/literature-review/SKILL.md): 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…
- [markitdown](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/markitdown/SKILL.md): 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 s…
- [open-notebook](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/open-notebook/SKILL.md): Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.
- [paper-lookup](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/paper-lookup/SKILL.md): Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with reproducible provenance.
- [paperclip](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/paperclip/SKILL.md): 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.
- [paperzilla](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/paperzilla/SKILL.md): Chat with your agent about projects, recommendations, and canonical papers in Paperzilla.
- [parallel-web](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/parallel-web/SKILL.md): 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 monit…
- [pyzotero](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pyzotero/SKILL.md): 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 bibli…
- [reference-manager-interop](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/reference-manager-interop/SKILL.md): Move and sync reference libraries between Zotero, Mendeley, EndNote, JabRef, Paperpile and writing tools (LaTeX/BibTeX, Word, Google Docs, Pandoc, Quarto, Overleaf).
- [research-lookup](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/research-lookup/SKILL.md): Compile current scholarly evidence for a scientific manuscript or research brief.
- [systematic-review-prisma](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/systematic-review-prisma/SKILL.md): Plan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards.

## ideation-and-design

- [analytical-method-validation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/analytical-method-validation/SKILL.md): Plans and evaluates analytical method validation, verification, and transfer using Python scripts (plan_validation, check_response, check_accuracy_precision, check_detection_limits, check_bioanalytic…
- [brainstorming-research-ideas](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/brainstorming-research-ideas/SKILL.md): Guides researchers through structured ideation frameworks to discover high-impact research directions.
- [consciousness-council](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/consciousness-council/SKILL.md): Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge.
- [creative-thinking-for-research](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/creative-thinking-for-research/SKILL.md): Applies cognitive science frameworks for creative thinking to CS and AI research ideation.
- [experimental-design](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/experimental-design/SKILL.md): Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable.
- [hypogenic](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/hypogenic/SKILL.md): Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets.
- [hypothesis-generation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/hypothesis-generation/SKILL.md): Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis…
- [iso-standards-readiness](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/iso-standards-readiness/SKILL.md): 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 test…
- [relsa-severity-assessment](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/relsa-severity-assessment/SKILL.md): Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting.
- [scientific-brainstorming](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-brainstorming/SKILL.md): Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.
- [statistical-power](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/statistical-power/SKILL.md): Sample-size and statistical power calculations for planning studies.
- [uncertainty-and-units](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/uncertainty-and-units/SKILL.md): Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties.

## data-science-and-ml

- [aeon](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/aeon/SKILL.md): This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.
- [dask](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/dask/SKILL.md): Distributed computing for larger-than-RAM pandas/NumPy workflows.
- [datalad](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/datalad/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/exploratory-data-analysis/SKILL.md): Perform bounded, local exploratory analysis of explicitly supported scientific files.
- [get-available-resources](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/get-available-resources/SKILL.md): 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.
- [hugging-science](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/hugging-science/SKILL.md): 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…
- [lamindb](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/lamindb/SKILL.md): Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models.
- [matlab](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/matlab/SKILL.md): 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 Project…
- [modal](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/modal/SKILL.md): Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.
- [networkx](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/networkx/SKILL.md): Create, analyze, and visualize complex networks and graphs in Python with NetworkX.
- [optimize-for-gpu](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/optimize-for-gpu/SKILL.md): GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster.
- [polars](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/polars/SKILL.md): High-performance DataFrame library for Python ETL, analytics, and pandas migration.
- [pufferlib](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pufferlib/SKILL.md): Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review.
- [pymc](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pymc/SKILL.md): Builds, fits, checks, and compares Bayesian models in Python with PyMC and ArviZ.
- [pymoo](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pymoo/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pytorch-lightning/SKILL.md): Organizes PyTorch training code with the lightning package (PyTorch Lightning): LightningModule, LightningDataModule, Trainer, callbacks such as ModelCheckpoint and EarlyStopping, loggers (TensorBoar…
- [scikit-learn](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scikit-learn/SKILL.md): Covers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction, preprocessing, Pipeline and ColumnTransform…
- [scikit-survival](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scikit-survival/SKILL.md): 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 cumu…
- [shap](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/shap/SKILL.md): Explain and audit machine-learning predictions with SHAP.
- [simpy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/simpy/SKILL.md): 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,…
- [stable-baselines3](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/stable-baselines3/SKILL.md): Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API.
- [statistical-analysis](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/statistical-analysis/SKILL.md): Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting.
- [statsmodels](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/statsmodels/SKILL.md): Statistical models library for Python.
- [sympy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/sympy/SKILL.md): Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX.
- [timesfm-forecasting](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/timesfm-forecasting/SKILL.md): Zero-shot time series forecasting with Google's TimesFM foundation model.
- [torch-geometric](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/torch-geometric/SKILL.md): PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets.
- [transformers](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/transformers/SKILL.md): Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.
- [umap-learn](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/umap-learn/SKILL.md): 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…
- [vaex](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/vaex/SKILL.md): 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.
- [zarr-python](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/zarr-python/SKILL.md): 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.

## visualization-and-presentation

- [academic-plotting](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/academic-plotting/SKILL.md): Generates publication-quality figures for ML papers from research context.
- [generate-image](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/generate-image/SKILL.md): Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow).
- [infographics](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/infographics/SKILL.md): 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 o…
- [latex-posters](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/latex-posters/SKILL.md): 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…
- [matplotlib](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/matplotlib/SKILL.md): Low-level plotting library for full customization.
- [pptx-posters](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pptx-posters/SKILL.md): Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets.
- [presenting-conference-talks](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/presenting-conference-talks/SKILL.md): Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script.
- [scientific-schematics](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-schematics/SKILL.md): 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 documen…
- [scientific-slides](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-slides/SKILL.md): Build slide decks and presentations for research talks.
- [scientific-visualization](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scientific-visualization/SKILL.md): Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly.
- [seaborn](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/seaborn/SKILL.md): Statistical visualization with pandas integration.

## knowledge-and-rag

- [chroma](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/chroma/SKILL.md): Open-source embedding database for AI applications.
- [faiss](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/faiss/SKILL.md): Facebook's library for efficient similarity search and clustering of dense vectors.
- [paper-corpus-rag](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/paper-corpus-rag/SKILL.md): 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.
- [pinecone](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pinecone/SKILL.md): Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations.
- [qdrant-vector-search](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/qdrant-vector-search/SKILL.md): High-performance vector similarity search engine for RAG and semantic search.
- [research-knowledge-graph](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/research-knowledge-graph/SKILL.md): 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…
- [sentence-transformers](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/sentence-transformers/SKILL.md): 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 mu…

## scientific-databases

- [bioservices](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/bioservices/SKILL.md): Unified Python interface to 40+ bioinformatics services.
- [cellxgene-census](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/cellxgene-census/SKILL.md): Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data.
- [database-lookup](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/database-lookup/SKILL.md): Query documented public database APIs with explicit endpoints, filters, pagination, and provenance.
- [depmap](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/depmap/SKILL.md): Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles.
- [genomic-coordinates](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/genomic-coordinates/SKILL.md): Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before they corrupt an analysis.
- [gget](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/gget/SKILL.md): 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, DIA…
- [imaging-data-commons](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/imaging-data-commons/SKILL.md): Query and download public cancer imaging data from NCI Imaging Data Commons.
- [ncats-arax](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ncats-arax/SKILL.md): Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships.
- [onekgpd](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/onekgpd/SKILL.md): Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants.
- [ontology-term-resolution](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ontology-term-resolution/SKILL.md): Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4).
- [pytdc](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pytdc/SKILL.md): 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_spl…
- [usfiscaldata](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/usfiscaldata/SKILL.md): Query the U.S.

## life-sciences

- [13c-metabolic-flux](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/13c-metabolic-flux/SKILL.md): 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…
- [alphagenome](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/alphagenome/SKILL.md): 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, C…
- [anndata](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/anndata/SKILL.md): Data structure for annotated matrices in single-cell analysis.
- [arboreto](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/arboreto/SKILL.md): Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3).
- [bids](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/bids/SKILL.md): 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, moti…
- [biopython](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/biopython/SKILL.md): 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, struc…
- [bulk-rnaseq](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/bulk-rnaseq/SKILL.md): 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 co…
- [cobrapy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/cobrapy/SKILL.md): Runs constraint-based metabolic modeling with COBRApy (Python, import cobra) on genome-scale models in SBML, JSON, YAML, or MATLAB format.
- [deeptools](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/deeptools/SKILL.md): 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 p…
- [esm](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/esm/SKILL.md): 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…
- [etetoolkit](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/etetoolkit/SKILL.md): Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4.
- [flowio](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/flowio/SKILL.md): Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO.
- [folklore-variant-evidence](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/folklore-variant-evidence/SKILL.md): 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 t…
- [geniml](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/geniml/SKILL.md): 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 B…
- [genomic-intelligence](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/genomic-intelligence/SKILL.md): 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.
- [gtars](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/gtars/SKILL.md): 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 s…
- [matchms](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/matchms/SKILL.md): Process, clean, compare, and search tandem mass spectra with matchms.
- [neurokit2](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/neurokit2/SKILL.md): Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity.
- [neuropixels-analysis](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/neuropixels-analysis/SKILL.md): Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface.
- [nextflow](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nextflow/SKILL.md): Build, run, and debug Nextflow data pipelines and nf-core workflows end to end.
- [pacsomatic](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pacsomatic/SKILL.md): Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs.
- [pathogen-variant-surveillance](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pathogen-variant-surveillance/SKILL.md): 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.
- [pathway-enrichment](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pathway-enrichment/SKILL.md): Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results.
- [polars-bio](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/polars-bio/SKILL.md): Python library polars-bio for genomic interval operations and bioinformatics file I/O on Polars DataFrames, built on Arrow and DataFusion.
- [pydeseq2](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pydeseq2/SKILL.md): Runs differential expression analysis on bulk RNA-seq count data with PyDESeq2, the Python port of DESeq2.
- [pyopenms](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pyopenms/SKILL.md): Complete mass spectrometry analysis platform.
- [pysam](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pysam/SKILL.md): Python/HTSlib workflows for genomic files.
- [scanpy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scanpy/SKILL.md): Standard single-cell RNA-seq analysis pipeline.
- [scikit-bio](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scikit-bio/SKILL.md): 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 diversit…
- [scvelo](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scvelo/SKILL.md): 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).
- [scvi-tools](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/scvi-tools/SKILL.md): 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 PyTo…
- [tiledbvcf](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/tiledbvcf/SKILL.md): Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat).
- [waypoint-bio](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/waypoint-bio/SKILL.md): 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 bench…

## chemistry-and-drug-discovery

- [adaptyv](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/adaptyv/SKILL.md): How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval.
- [datamol](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/datamol/SKILL.md): Wraps RDKit through the datamol Python library (import datamol as dm) for molecular cheminformatics, returning native rdkit.Chem.Mol objects.
- [deepchem](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/deepchem/SKILL.md): Molecular ML with diverse featurizers and pre-built datasets.
- [diffdock](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/diffdock/SKILL.md): DiffDock and DiffDock-L molecular docking.
- [medchem](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/medchem/SKILL.md): Filters and triages small-molecule libraries with the Python medchem library (datamol-io, v2.0.5) on top of RDKit and datamol.
- [molecular-dynamics](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/molecular-dynamics/SKILL.md): Runs and analyzes molecular dynamics simulations using OpenMM and MDAnalysis.
- [molfeat](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/molfeat/SKILL.md): 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.
- [pkpd-modeling](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pkpd-modeling/SKILL.md): Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allome…
- [rdkit](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/rdkit/SKILL.md): 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 se…
- [rowan](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/rowan/SKILL.md): Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API.
- [tamarind](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/tamarind/SKILL.md): 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.
- [torchdrug](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/torchdrug/SKILL.md): Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and know…

## clinical-and-health

- [clinical-decision-support](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/clinical-decision-support/SKILL.md): Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts.
- [clinical-reports](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/clinical-reports/SKILL.md): 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,…
- [histolab](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/histolab/SKILL.md): Extracts tiles and preprocesses H&E whole slide images with the histolab Python library (OpenSlide), covering slide inspection, tissue masks (TissueMask, BiggestTissueBoxMask), RandomTiler, GridTiler…
- [pathml](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pathml/SKILL.md): 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…
- [pydicom](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pydicom/SKILL.md): 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, p…
- [pyhealth](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pyhealth/SKILL.md): Builds clinical deep-learning pipelines with PyHealth using its Dataset → Task → Model → Trainer → Metrics pattern.
- [treatment-plans](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/treatment-plans/SKILL.md): Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals.

## physical-sciences

- [astropy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/astropy/SKILL.md): 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.
- [cirq](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/cirq/SKILL.md): Google quantum computing framework.
- [fluidsim](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/fluidsim/SKILL.md): Plan, configure, inspect, restart, and analyze bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety checks.
- [geomaster](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/geomaster/SKILL.md): 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,…
- [geopandas](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/geopandas/SKILL.md): 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,…
- [openpiv](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/openpiv/SKILL.md): Particle Image Velocimetry (PIV) analysis with OpenPIV.
- [pennylane](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pennylane/SKILL.md): Hardware-agnostic quantum ML framework with automatic differentiation.
- [pymatgen](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pymatgen/SKILL.md): Analyzes, validates, converts, and transforms crystal structures and molecules with pymatgen.
- [qiskit](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/qiskit/SKILL.md): Build, simulate, transpile, and execute quantum circuits with Qiskit and IBM Quantum Runtime.
- [qutip](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/qutip/SKILL.md): Simulate and audit closed and open quantum-system models with QuTiP 5, including deterministic, trajectory, steady-state, spectral, and phase-space workflows.

## lab-automation

- [benchling-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/benchling-integration/SKILL.md): Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries.
- [dnanexus-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/dnanexus-integration/SKILL.md): Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow.
- [fictiv](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/fictiv/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ginkgo-cloud-lab/SKILL.md): 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).
- [lab-hardware-cad](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/lab-hardware-cad/SKILL.md): 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, c…
- [labarchive-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/labarchive-integration/SKILL.md): Securely integrate with the official LabArchives ELN REST-like API and Inventory API v1.
- [latchbio-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/latchbio-integration/SKILL.md): 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.
- [omero-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/omero-integration/SKILL.md): 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.
- [opentrons-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/opentrons-integration/SKILL.md): Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots.
- [protocolsio-integration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/protocolsio-integration/SKILL.md): 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.
- [pylabrobot](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pylabrobot/SKILL.md): Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations.

## research-automation

- [ara-compiler](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ara-compiler/SKILL.md): 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, con…
- [ara-research-manager](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ara-research-manager/SKILL.md): 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/ directo…
- [ara-rigor-reviewer](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ara-rigor-reviewer/SKILL.md): 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.
- [arbor](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/arbor/SKILL.md): 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.
- [autoresearch](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/autoresearch/SKILL.md): Orchestrates end-to-end autonomous AI research projects using a two-loop architecture.
- [autoskill](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/autoskill/SKILL.md): 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)…
- [pi-agent](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pi-agent/SKILL.md): Build with and use Pi, the minimal terminal coding harness.
- [research-agent-skills](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/research-agent-skills/SKILL.md): Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic writing.
- [research-skill-creator](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/research-skill-creator/SKILL.md): 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 qualit…

## ml-training

- [awq-quantization](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/awq-quantization/SKILL.md): Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.
- [axolotl](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/axolotl/SKILL.md): 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 mul…
- [deepspeed](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/deepspeed/SKILL.md): 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_ha…
- [distributed-llm-pretraining-torchtitan](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/distributed-llm-pretraining-torchtitan/SKILL.md): Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).
- [fine-tuning-with-trl](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/fine-tuning-with-trl/SKILL.md): 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.
- [gguf-quantization](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/gguf-quantization/SKILL.md): GGUF format and llama.cpp quantization for efficient CPU/GPU inference.
- [gptq](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/gptq/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/grpo-rl-training/SKILL.md): Guides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple reward functions (correctness, format, le…
- [hqq-quantization](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/hqq-quantization/SKILL.md): Half-Quadratic Quantization for LLMs without calibration data.
- [huggingface-accelerate](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/huggingface-accelerate/SKILL.md): 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…
- [huggingface-tokenizers](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/huggingface-tokenizers/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/implementing-llms-litgpt/SKILL.md): Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).
- [llama-factory](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/llama-factory/SKILL.md): 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 multimod…
- [mamba-architecture](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/mamba-architecture/SKILL.md): 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.
- [miles-rl-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/miles-rl-training/SKILL.md): Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.
- [ml-training-recipes](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ml-training-recipes/SKILL.md): Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics.
- [nanogpt](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nanogpt/SKILL.md): 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 mul…
- [openrlhf-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/openrlhf-training/SKILL.md): High-performance RLHF framework with Ray+vLLM acceleration.
- [optimizing-attention-flash](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/optimizing-attention-flash/SKILL.md): 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, a…
- [peft-fine-tuning](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/peft-fine-tuning/SKILL.md): 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](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pytorch-fsdp2/SKILL.md): Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing.
- [pytorch-lightning-distributed](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pytorch-lightning-distributed/SKILL.md): High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate.
- [quantizing-models-bitsandbytes](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/quantizing-models-bitsandbytes/SKILL.md): Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss.
- [ray-train](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ray-train/SKILL.md): Distributed training orchestration across clusters.
- [rwkv-architecture](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/rwkv-architecture/SKILL.md): 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 i…
- [sentencepiece](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/sentencepiece/SKILL.md): Language-independent tokenizer treating text as raw Unicode.
- [simpo-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/simpo-training/SKILL.md): Simple Preference Optimization for LLM alignment.
- [slime-rl-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/slime-rl-training/SKILL.md): Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework.
- [torchforge-rl-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/torchforge-rl-training/SKILL.md): Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms.
- [training-llms-megatron](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/training-llms-megatron/SKILL.md): 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…
- [unsloth](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/unsloth/SKILL.md): 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).
- [verl-rl-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/verl-rl-training/SKILL.md): Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).

## ml-evaluation-and-safety

- [constitutional-ai](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/constitutional-ai/SKILL.md): Anthropic's method for training harmless AI through self-improvement.
- [evaluating-code-models](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/evaluating-code-models/SKILL.md): Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.
- [evaluating-llms-harness](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/evaluating-llms-harness/SKILL.md): Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).
- [llamaguard](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/llamaguard/SKILL.md): 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 subs…
- [nemo-evaluator-sdk](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nemo-evaluator-sdk/SKILL.md): Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.
- [nemo-guardrails](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nemo-guardrails/SKILL.md): Adds runtime safety rails to LLM applications with NVIDIA NeMo Guardrails, configured through Colang 2.0 flows.
- [nnsight-remote-interpretability](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nnsight-remote-interpretability/SKILL.md): Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.
- [prompt-guard](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/prompt-guard/SKILL.md): 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 applicat…
- [pyvene-interventions](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/pyvene-interventions/SKILL.md): Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework.
- [sparse-autoencoder-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/sparse-autoencoder-training/SKILL.md): Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features.
- [transformer-lens-interpretability](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/transformer-lens-interpretability/SKILL.md): Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching.

## ml-inference-and-ops

- [experiment-tracking-swanlab](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/experiment-tracking-swanlab/SKILL.md): 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 clo…
- [lambda-labs-gpu-cloud](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/lambda-labs-gpu-cloud/SKILL.md): Reserved and on-demand GPU cloud instances for ML training and inference.
- [langsmith-observability](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/langsmith-observability/SKILL.md): LLM observability platform for tracing, evaluation, and monitoring.
- [llama-cpp](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/llama-cpp/SKILL.md): Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.
- [mlflow](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/mlflow/SKILL.md): 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 Hugg…
- [modal-serverless-gpu](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/modal-serverless-gpu/SKILL.md): Serverless GPU cloud platform for running ML workloads.
- [phoenix-observability](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/phoenix-observability/SKILL.md): Open-source AI observability platform for LLM tracing, evaluation, and monitoring.
- [serving-llms-vllm](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/serving-llms-vllm/SKILL.md): Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.
- [sglang](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/sglang/SKILL.md): Fast structured generation and serving for LLMs with RadixAttention prefix caching.
- [skypilot-multi-cloud-orchestration](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/skypilot-multi-cloud-orchestration/SKILL.md): Multi-cloud orchestration for ML workloads with automatic cost optimization.
- [tensorboard](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/tensorboard/SKILL.md): 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,…
- [tensorrt-llm](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/tensorrt-llm/SKILL.md): Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.
- [weights-and-biases](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/weights-and-biases/SKILL.md): 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 rep…

## llm-applications

- [autogpt-agents](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/autogpt-agents/SKILL.md): Autonomous AI agent platform for building and deploying continuous agents.
- [crewai-multi-agent](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/crewai-multi-agent/SKILL.md): Multi-agent orchestration framework for autonomous AI collaboration.
- [dspy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/dspy/SKILL.md): Builds and optimizes language model programs with DSPy (Stanford NLP), using Signatures, modules (Predict, ChainOfThought, ReAct, ProgramOfThought) and optimizers (BootstrapFewShot, MIPRO, BootstrapF…
- [evolving-ai-agents](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/evolving-ai-agents/SKILL.md): Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms.
- [guidance](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/guidance/SKILL.md): Constrains LLM output during generation with Guidance (Microsoft Research), using regex, select() choices, context-free grammars, token healing, and @guidance functions, with Anthropic, OpenAI, Trans…
- [instructor](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/instructor/SKILL.md): 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 val…
- [langchain](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/langchain/SKILL.md): Framework for building LLM-powered applications with agents, chains, and RAG.
- [llamaindex](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/llamaindex/SKILL.md): Data framework for building LLM applications with RAG.
- [outlines](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/outlines/SKILL.md): 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 int…

## multimodal-and-emerging

- [audiocraft-audio-generation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/audiocraft-audio-generation/SKILL.md): PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen).
- [blip-2-vision-language](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/blip-2-vision-language/SKILL.md): 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 answ…
- [clip](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/clip/SKILL.md): OpenAI's model connecting vision and language.
- [evaluating-cosmos-policy](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/evaluating-cosmos-policy/SKILL.md): Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments.
- [fine-tuning-openvla-oft](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/fine-tuning-openvla-oft/SKILL.md): 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-wor…
- [fine-tuning-serving-openpi](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/fine-tuning-serving-openpi/SKILL.md): 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.
- [knowledge-distillation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/knowledge-distillation/SKILL.md): Compress large language models using knowledge distillation from teacher to student models.
- [llava](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/llava/SKILL.md): Large Language and Vision Assistant.
- [long-context](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/long-context/SKILL.md): Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques.
- [model-merging](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/model-merging/SKILL.md): Merge multiple fine-tuned models using mergekit to combine capabilities without retraining.
- [model-pruning](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/model-pruning/SKILL.md): Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT.
- [moe-training](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/moe-training/SKILL.md): Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace.
- [nemo-curator](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/nemo-curator/SKILL.md): GPU-accelerated data curation for LLM training.
- [ray-data](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/ray-data/SKILL.md): Scalable data processing for ML workloads.
- [segment-anything-model](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/segment-anything-model/SKILL.md): Foundation model for image segmentation with zero-shot transfer.
- [speculative-decoding](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/speculative-decoding/SKILL.md): Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques.
- [stable-diffusion-image-generation](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/stable-diffusion-image-generation/SKILL.md): 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 condi…
- [whisper](https://raw.githubusercontent.com/KalarisLabs/research-agent-skills/main/skills/whisper/SKILL.md): 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, wo…