Agent-Skills / Skills
AGENTS.md9 starsChanged 46 days agoApache-2.0View on GitHub
- Treat this subtree as canonical first-party skill source. Runtime projections under .agents/**, .skillsets/**, or user home links are generated views, not the source to edit. - Before changing skills, sync policy, runtime projections, or agent-facing docs, read UBIQUITOUS_LANGUAGE.md. - Keep each SKILL.md focused. Move bulky detail to nearby references/**, scripts/**, assets/**, or templates, then leave a clear route from the skill entrypoint. - Do not claim a skill is runtime-usable from source existence alone. Prove the runtime projection or…
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 repository93 other files it gives its agents.
- AGENTS.mdAGENTS.md
- artifacts/AGENTS.mdAGENTS.md
- Docs/AGENTS.mdAGENTS.md
- Infrastructure/AGENTS.mdAGENTS.md
- logs/AGENTS.mdAGENTS.md
- Plugins/AGENTS.mdAGENTS.md
- skills-system/AGENTS.mdAGENTS.md
- Wiki/AGENTS.mdAGENTS.md
- SKILL.mdSkill
- agents-mdSkill
- alignment-checkpointSkill
- autofixSkill
- autoresearchSkill
- autoreviewSkill
- bash-hygieneSkill
- biome-lintingSkill
- bootstrapSkill
- code-fixes-triageSkill
- codex-agent-creatorSkill
- codex-automation-architectSkill
- codex-environment-creatorSkill
- codex-hooks-builderSkill
- codex-reviewSkill
- coding-harnessSkill
- context7Skill
- decide-build-primitiveSkill
- diagram-cliSkill
- elixir-proSkill
- evals-routerSkill
- fix-miseSkill
- frontend-designSkill
- goal-governorSkill
- goSkill
- improve-agent-nativeSkill
- improve-codebase-architectureSkill
- insight-reportSkill
- javascript-proSkill
- keep-codex-fastSkill
- npm-releaseSkill
- pnpm-managerSkill
- prek-proSkill
- pr-green-sweepSkill
- production-deploymentSkill
- project-brainSkill
- rust-proSkill
- sdk-scenario-generatorSkill
- session-workflow-minerSkill
- simplifySkill
- skill-pr-deliverySkill
- technical-writerSkill
- testingSkill
- tomlSkill
- triageSkill
- typescriptSkill
- ubiquitous-languageSkill
- unslopifySkill
- user-documentationSkill
- uv-python-project-setupSkill
- valeSkill
- verification-before-completionSkill
- The first 60 shown.
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 14
Treat this subtree as canonical first-party skill source.
- Very specific: line 17
Before changing skills, sync policy, runtime projections, or agent-facing docs, read UBIQUITOUS_LANGUAGE.md.
- Very specific: line 19
Keep each SKILL.md focused.
- Distinctive: line 22
Do not claim a skill is runtime-usable from source existence alone.
≈ “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
Skills Agent Guide
Scope
- Applies to
Skills/**. - Inherits the repository root AGENTS.md.
Edit Policy
- Treat this subtree as canonical first-party skill source. Runtime projections
under
.agents/**,.skillsets/**, or user home links are generated views, not the source to edit. - Before changing skills, sync policy, runtime projections, or agent-facing docs, read UBIQUITOUS_LANGUAGE.md.
- Keep each
SKILL.mdfocused. Move bulky detail to nearbyreferences/**,scripts/**,assets/**, or templates, then leave a clear route from the skill entrypoint. - Do not claim a skill is runtime-usable from source existence alone. Prove the runtime projection or state the boundary as source inspection only.
Context Pointers
- Skill lifecycle rules: ../Docs/agents/17-skill-management.md.
- Skill Factory routing and lifecycle map: ../Plugins/skill-factory/README.md.
- Path ownership: ../Docs/agents/14-path-ownership-boundaries.md.
- Skill templates:
Infrastructure/templates/**.
Route skill work through the Skill Factory lanes: use
the Codex .system/skill-creator with attached Skill Factory references for first usable package shape,
skill-factory:skillify for repeatable-workflow capture,
skill-factory:skill-builder for audit and hardening,
skill-factory:skill-refactor for evidence-based keep/merge/split/retire
decisions, and the Codex .system/skill-installer with attached Skill Factory
references for install, sync, and runtime visibility. Use skill-factory:skill-factory-router when the request needs
classification before one of those lanes.
Validation
- For skill content changes, run the strictest practical skill audit or the
relevant
./bin/ask skills ... --json --robotcommand. - For projection changes, regenerate through the repo wrapper and validate freshness; never hand-edit generated projection files.
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.