agent-skills
AGENTS.md1 starsChanged 36 days agoMITView on GitHub
Portable agent skill library for reusable agent workflows. Copy all skills into the active skills directory:
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 repository10 other files it gives its agents.
- 60-30-10Skill
- buildSkill
- explainerSkill
- explainSkill
- icm-architectSkill
- karpathy-guidelinesSkill
- skill-tuneSkill
- swarmSkill
- weekly-signal-diff-aiSkill
- write-discoverable-codeSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 1 is common, 6 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Keep the repo small.
- Distinctive: line 21
Do not flatten skill folders.
- Distinctive: line 22
Do not add generated artifacts or local agent settings.
- Common: line 26
Do not publish secrets.
- Distinctive: line 27
Do not add cloud deployment automation.
- Distinctive: line 28
Do not add repo-specific test fixtures unless this becomes a test harness repo.
- Distinctive: line 29
Do not rewrite imported skills unless the user asks to modify that skill.
≈ “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
agent-skill-repo
What This Is
Portable agent skill library for reusable agent workflows.
How To Use It
Copy all skills into the active skills directory:
cp -R skills/* ~/.agents/skills/Conventions
- Keep the repo small.
- Each skill lives under
skills/<skill-name>/. - Each skill's source of truth is its
SKILL.md. - Preserve bundled
references/,scripts/,agents/, and other skill-local resources. - Do not flatten skill folders.
- Do not add generated artifacts or local agent settings.
Do Not Do Without Asking
- Do not publish secrets.
- Do not add cloud deployment automation.
- Do not add repo-specific test fixtures unless this becomes a test harness repo.
- Do not rewrite imported skills unless the user asks to modify that skill.
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.