agents
AGENTS.md21 starsChanged 10 days agoMITView on GitHub
This repository contains reusable agent skills: - skills/<skill-name>/SKILL.md is required for every skill. - skills/<skill-name>/agents/openai.yaml contains optional OpenAI UI metadata. - skills/<skill-name>/assets/ contains icons and other bundled assets. - skills/<skill-name>/references/ contains longer supporting docs. - scripts/ contains repository tooling. - .github/workflows/ contains CI configuration. - .skill-ref/ is a local bootstrap clone for validation tooling; do not edit it as source. Run all checks before finishing changes: Run validation without formatting: Requires Make, Node.js 24+, uv, and Claude Code. Run make…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- denysdovhan/skillsword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- denysdovhan/skills★ 21100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- agent-logSkill
- commitSkill
- interactive-debuggingSkill
- readable-codeSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Run all checks before finishing changes:
- Distinctive: line 24
Run validation without formatting:
- Very specific: line 36
Use Markdown for skill instructions and YAML for metadata.
- Very specific: line 43
When creating or substantially updating skills, all agents must use the skill-creator skill and follow its guidance before editing skill …
- Very specific: line 55
Use conventional commits with a concise imperative subject, for example feat: add agent-log skill or docs: add skill icons to README.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
Repository Guidelines
Project Structure & Module Organization
This repository contains reusable agent skills:
skills/<skill-name>/SKILL.mdis required for every skill.skills/<skill-name>/agents/openai.yamlcontains optional OpenAI UI metadata.skills/<skill-name>/assets/contains icons and other bundled assets.skills/<skill-name>/references/contains longer supporting docs.scripts/contains repository tooling..github/workflows/contains CI configuration..skill-ref/is a local bootstrap clone for validation tooling; do not edit it as source.
Build, Test, and Development Commands
Run all checks before finishing changes:
make checkRun validation without formatting:
make validateRequires Make, Node.js 24+, uv, and Claude Code. Run make install to install hooks.
The scripts validate skills, plugin schemas, and marketplace consistency.
There is no build step.
Coding Style & Naming Conventions
Use Markdown for skill instructions and YAML for metadata. Skill directory names
must match the name field in SKILL.md, using lowercase hyphenated names
such as home-assistant-integration. Keep SKILL.md focused on actionable
workflow guidance. Put reusable reference material in references/ instead of
expanding the main skill file unnecessarily. Use relative asset paths in
agents/openai.yaml, for example ./assets/git.png.
When creating or substantially updating skills, all agents must use the
skill-creator skill and follow its guidance before editing skill files.
Testing Guidelines
Validation is schema-based through skills-ref; there are no unit tests or
coverage targets. Add or update assets and references only when they are used by
a skill or its metadata. After changing SKILL.md, metadata, references, or
assets, run make validate and git diff --check.
Commit & Pull Request Guidelines
Use conventional commits with a concise imperative subject, for example
feat: add agent-log skill or docs: add skill icons to README. Keep commits
focused by skill or concern.
Pull requests should summarize what skill changed, why it changed, and which validation commands passed. Include screenshots only when UI-facing icon or README rendering changes need visual review.
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.