agent-skills
AGENTS.md2 starsChanged 12 days agoMITView on GitHub
Read CONTINUATION.md before resuming. Keep the full package and article objective visible there. Skills live in skills/<name>/SKILL.md. Each must work from its own folder with relative references and must describe a distinct task. Preserve the user's chosen tools and scope. Explain platform-specific capabilities as adapters; do not require a particular agent or a running service for a generic method. Write new instructions, not copies of private project documents. Record source revisions in PROVENANCE.md. Do not vendor third-party suites, source projects,…
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 repository11 other files it gives its agents.
- aeoSkill
- agent-worktree-orchestrationSkill
- critical-adversarial-reviewSkill
- evidence-driven-debuggingSkill
- gauntlet-loopSkill
- git-quality-hooksSkill
- multi-agent-collaborationSkill
- quality-gatesSkill
- source-backed-researchSkill
- spec-to-planSkill
- validated-coding-loopSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read CONTINUATION.md before resuming.
- Very specific: line 7
Write new instructions, not copies of private project documents.
- Very specific: line 9
Run npm run check after package changes.
- Distinctive: line 11
Do not activate these skills globally as a side effect of editing the collection.
≈ “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
Working on this collection
Read CONTINUATION.md before resuming. Keep the full package and article objective visible there.
Skills live in skills/<name>/SKILL.md. Each must work from its own folder with relative references and must describe a distinct task. Preserve the user's chosen tools and scope. Explain platform-specific capabilities as adapters; do not require a particular agent or a running service for a generic method.
Write new instructions, not copies of private project documents. Record source revisions in PROVENANCE.md. Do not vendor third-party suites, source projects, credentials, customer data, or generated bulk artifacts. Keep skill content separate from article and release notes.
Run npm run check after package changes. Run the documented focused fixture checks after changing executable examples. A structural check does not prove model behavior. Keep real-agent evaluations and publication status explicit.
Do not activate these skills globally as a side effect of editing the collection. Preserve existing hooks when helping a user install hook examples.
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.