skills
AGENTS.md3 starsChanged 43 days agoMITView on GitHub
Skills in skills/ are the editable source of truth. Keep adopted files and their attribution intact unless intentionally changing them; skills.json records provenance and profile membership. Add new skills to that manifest. Use scripts/skillset.py --help for installation and checks. Instructions in routines/ are read in place by scheduled Claude routines. They aren't skills: keep them out of skills.json, and update the routine prompts in ~/.claude/scheduled-tasks/ if you move them. When importing or updating a skill, preserve local edits, inspect its…
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
When importing or updating a skill, preserve local edits, inspect its resources, and resolve duplicate names or nested skill roots before …
- Very specific: line 9
Run pnpm test after changes.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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
Working here
Skills in skills/ are the editable source of truth. Keep adopted files and their attribution intact unless intentionally changing them; skills.json records provenance and profile membership. Add new skills to that manifest. Use scripts/skillset.py --help for installation and checks.
Instructions in routines/ are read in place by scheduled Claude routines. They aren't skills: keep them out of skills.json, and update the routine prompts in ~/.claude/scheduled-tasks/ if you move them.
When importing or updating a skill, preserve local edits, inspect its resources, and resolve duplicate names or nested skill roots before installation. Use a temporary checkout for upstream comparisons; install from this repo rather than letting an upstream installer overwrite its links.
Run pnpm test after changes. Installer tests run independently with python3 -m unittest discover -s tests. Keep READMEs short and practical, with a copyable agent setup prompt; put operational exceptions in docs/setup.md.
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 28,693 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 repository52 other files it gives its agents.
- skills/vercel-optimize/AGENTS.mdAGENTS.md
- skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- animation-vocabularySkill
- auto-researchSkill
- better-accessibilitySkill
- better-colorsSkill
- better-layoutSkill
- better-typographySkill
- better-uiSkill
- better-writingSkill
- birdclawSkill
- branding-exerciseSkill
- claudeSkill
- codebase-designSkill
- codexSkill
- compare-screenshotsSkill
- create-verification-skillSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- eli5Skill
- eval-skillsSkill
- find-skillsSkill
- good-cssSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- impeccableSkill
- implementSkill
- improve-animationsSkill
- improve-codebase-architectureSkill
- improve-uiSkill
- init-git-repoSkill
- maintain-verification-skillSkill
- midjourney-imagesSkill
- personal-notion-projectsSkill
- phaseSkill
- prototypeSkill
- researchSkill
- retroSkill
- review-animationsSkill
- shadcnSkill
- show-meSkill
- storytellingSkill
- testing-strategySkill
- unslopSkill
- variantSkill
- vercel-optimizeSkill
- vercel-react-best-practicesSkill
- web-perfSkill
- write-skillsSkill
- x-dataSkill
- xurlSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.