claude-skills
llms.txt0 starsChanged 5 months agoMITView on GitHub
A curated collection of self-contained skills for Claude Code (and other AI coding agents). Each skill is one folder under skills/ that you copy into ~/.claude/skills/. Battle-tested while shipping real products, then de-personalized to be reusable. Each skill is independent and has its own SKILL.md (the procedure an agent follows) and README.md (the human quickstart). The full index is in catalog.json.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- annotateSkill
- debug-loop-breakerSkill
- deploy-checklistSkill
- goalSkill
- growth-playbookSkill
- security-scannerSkill
- seo-auditSkill
- svg-diagramSkill
- tdd-disciplineSkill
- teaching-modeSkill
- verify-frontend-changeSkill
- SKILL_NAMESkill
The file
Files
# claude-skills > A curated collection of self-contained skills for Claude Code (and other AI coding > agents). Each skill is one folder under skills/ that you copy into ~/.claude/skills/. > Battle-tested while shipping real products, then de-personalized to be reusable. Each skill is independent and has its own SKILL.md (the procedure an agent follows) and README.md (the human quickstart). The full index is in catalog.json. ## Start here - [README](README.md): what this is, how to install a skill, the catalog - [AGENTS.md](AGENTS.md): how an AI agent should discover, use, and install skills here - [CONTRIBUTING](CONTRIBUTING.md): how to add a skill (the contract + the publish gate) - [catalog.json](catalog.json): machine-readable index of every skill ## Tooling - [tools/check-skill.sh](tools/check-skill.sh): publish gate — scans a skill for secrets and personalization - [tools/new-skill.sh](tools/new-skill.sh): scaffold a new skill from the template - [tools/build-catalog.py](tools/build-catalog.py): regenerate the index from the skills (don't hand-edit the catalog) ## Skills See catalog.json for the live list. Each entry maps to skills/<name>/SKILL.md.
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.