skills
AGENTS.md0 starsChanged 5 days agoMITView on GitHub
Write skill instructions, descriptions, internal prompts, supporting documentation, and code comments in English. Keep unslop-br entirely in Brazilian Portuguese. Preserve Portuguese trigger examples, proper names, quoted source material, and localization catalogs when their language is part of their function. Use the user's language for conversation and follow each target project's language conventions for generated prose. English instructions do not require English output. Keep interface localization separate from instruction translation.
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 31,700 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 repository25 other files it gives its agents.
- archifySkill
- babysit-prsSkill
- boardSkill
- break-uiSkill
- clean-crapSkill
- goal-briefSkill
- graphifySkill
- grillingSkill
- humanizerSkill
- mobile-nativeSkill
- pr-descriptionSkill
- pr-loopSkill
- prune-agent-configSkill
- publication-hygieneSkill
- researchSkill
- review-lessonSkill
- setupSkill
- show-meSkill
- skill-evalSkill
- teachSkill
- to-specSkill
- to-ticketsSkill
- unslop-brSkill
- validate-agent-configSkill
- writing-for-agentsSkill
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 5
Write skill instructions, descriptions, internal prompts, supporting documentation, and code comments in English.
- Distinctive: line 7
Use the user's language for conversation and follow each target project's language conventions for generated prose.
- Very specific: line 10
Run node --test tests/, and npm test --prefix skills/clean-crap after npm ci --prefix skills/clean-crap.
- Very specific: line 18
Use the single-context convention (GLOSSARY.md, docs/adr/).
≈ “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 skills
Language conventions
Write skill instructions, descriptions, internal prompts, supporting documentation, and code comments in English. Keep unslop-br entirely in Brazilian Portuguese. Preserve Portuguese trigger examples, proper names, quoted source material, and localization catalogs when their language is part of their function.
Use the user's language for conversation and follow each target project's language conventions for generated prose. English instructions do not require English output. Keep interface localization separate from instruction translation.
Tests
Run node --test tests/, and npm test --prefix skills/clean-crap after npm ci --prefix skills/clean-crap. node skills/setup/scripts/generate-hub.mjs --fixture smokes the Project Hub generator, and bash skills/validate-agent-config/scripts/validate.sh lints the catalog and the installed skill roots (run ./link.sh first; errors outside skills/ describe the machine, not the change).
Issue tracker
Track issues locally in Markdown files under .scratch/<feature>/ on the primary worktree.
The interactive dashboard is at .scratch/index.html.
See docs/agents/issue-tracker.md.
Domain docs
Use the single-context convention (GLOSSARY.md, docs/adr/). See docs/agents/domain.md.
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.