skills
AGENTS.md4 starsChanged 2 months agoMITView on GitHub
This repository is the canonical source for installable skills.
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 32,671 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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-voiceSkill
- babysitSkill
- changelogSkill
- commitSkill
- desert-modeSkill
- dispatchSkill
- handbackSkill
- handoffSkill
- mailboxSkill
- open-prSkill
- quickchartSkill
- reviewSkill
- session-usageSkill
- spawnSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Put authored skills in skills/<skill-name>/.
- Very specific: line 8
Keep local install directories such as .agents/, .claude/, and .cursor/ out of version control.
- Very specific: line 9
Do not copy third-party skills into this repo.
- Distinctive: line 10
When adding or changing a visible skill, update README.md.
- Very specific: line 11
Treat the top-level LICENSE as applying to authored content only.
- Distinctive: line 13
If a skill isn't authored by the repo owner, the skill must also carry some attribution to its source.
- Very specific: line 17
Prefer validating repo discovery with npx skills add .
- Very specific: line 18
Ensure every installable skill has a valid SKILL.md with name and description frontmatter.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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 Guidance
This repository is the canonical source for installable skills.
Rules
- Put authored skills in
skills/<skill-name>/. - Keep local install directories such as
.agents/,.claude/, and.cursor/out of version control. - Do not copy third-party skills into this repo.
- When adding or changing a visible skill, update
README.md. - Treat the top-level
LICENSEas applying to authored content only. - Each skill entry in the top-level
README.mdmust link the skill name to itsSKILL.md.- If a skill isn't authored by the repo owner, the skill must also carry some attribution to its source.
Validation
- Prefer validating repo discovery with
npx skills add . --list. - Ensure every installable skill has a valid
SKILL.mdwithnameanddescriptionfrontmatter.
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.

