skills
CLAUDE.md170 starsChanged 3 months agoMITView on GitHub
Each skill is a folder directly under skills/, holding a SKILL.md. A skill can also carry an agents/openai.yaml (Codex metadata) and a references/ folder for material the SKILL.md points to. Some skills call skills that this repo does not contain — for example /grilling or /prototype. The README.md skill index names each skill's external dependencies. Install those separately. Every SKILL.md is user-invoked or model-invoked. A user-invoked skill sets disable-model-invocation: true in its front matter and policy.allow_implicit_invocation: false in agents/openai.yaml; only…
In this repository10 other files it gives its agents.
- agent-toolsSkill
- cmuxSkill
- code-storySkill
- development-workflowSkill
- grilling-frontend-prototypingSkill
- find-standardsSkill
- flashlightSkill
- grill-designSkill
- sandcastleSkill
- test-a-skillSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
Every SKILL.md is user-invoked or model-invoked.
- Very specific: line 9
When you add, rename, or remove a skill, update the README.md skill index to match, then run scripts/check-skills.sh until it passes.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Each skill is a folder directly under skills/, holding a SKILL.md. A skill can also carry an agents/openai.yaml (Codex metadata) and a references/ folder for material the SKILL.md points to.
Some skills call skills that this repo does not contain — for example /grilling or /prototype. The README.md skill index names each skill's external dependencies. Install those separately.
Every SKILL.md is user-invoked or model-invoked. A user-invoked skill sets disable-model-invocation: true in its front matter and policy.allow_implicit_invocation: false in agents/openai.yaml; only the human starts it. A model-invoked skill sets neither, so the agent can also reach it.
To link every skill into the local harness skill directories (~/.claude/skills, ~/.agents/skills), run scripts/link-skills.sh. Each entry is a symlink into this repo, so a git pull keeps the installed skills current. Run the script again after you add, remove, or rename a skill.
When you add, rename, or remove a skill, update the README.md skill index to match, then run scripts/check-skills.sh until it passes. It enforces every rule above, and CI runs it on each push and pull request.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.