Installation
One command
--project for the current repository instead.
The installer has explicit targets for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode,
Windsurf and generic .agents/skills consumers. Other harnesses need to support the Agent Skills folder format;
tool permissions and advanced metadata can differ.
Choose what to install
installed, update, uninstall <skills|--all> and doctor.
The CLI only ever removes skills it installed itself.
The curated --bundle choices are research-essentials, ml-research, ai-research,
biology-research, chemistry-research, medicine-research and physics-research.
Use individual skill names or --category when the bundle is too broad or too narrow.
Alternatives
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 indexes all 280 specialist skills. Each specialist remains separately installable. To install the entire collection into this project for Codex, run:--global for a user-wide install.
The public repository’s skills/<name>/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.
The directory’s rankings use the CLI’s anonymous install telemetry.
Python for skill scripts
Skills with ascripts/ folder run Python 3.9+ (many are standard-library only). For skills with
dependencies, install uv. npx research-agent-skills doctor checks your setup.