agent-skills / skills
AGENTS.md13 starsChanged 37 days agoApache-2.0View on GitHub
Each subdirectory is a self-contained, independently deployable agent skill following the Agent Skills specification. Copy a template from templates/ (api-skill, cli-skill, or workflow-skill) and follow its README checklist.
The file
Files
Skills Directory
Each subdirectory is a self-contained, independently deployable agent skill following the Agent Skills specification.
Skill Structure
skills/<name>/
├── SKILL.md # Documentation + YAML frontmatter (required)
├── scripts/
│ └── <name>.py # Python implementation
└── references/ # Optional supplementary docsRunning Checks for a Single Skill
- Validate structure:
python scripts/validate_skill.py skills/<name>/SKILL.md - Run tests:
pytest tests/test_<name>.py
Creating a New Skill
Copy a template from templates/ (api-skill, cli-skill, or workflow-skill)
and follow its README checklist.
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.