sorafujitanisorafujitani/skills/AGENTS.md

skills

AGENTS.md8 starsChanged 2 months agoMITView on GitHub

- This checkout owns standalone personal skills. Edit the real package here; ~/.agents/skills, ~/.codex/skills, and ~/.claude/skills are discovery paths. - When using skill-creator or another skill-authoring workflow, explicitly set its output directory to this checkout for standalone personal skills. Validate the completed package, register it with manage_skills.py register, then run check; generating files alone does not complete local registration. - Resolve an existing skill through the local manifest before updating it. Repository-scoped skills, plugin skills, and app-managed artifact templates keep…

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 repository20 other files it gives its agents.
- agent-efficiency-auditSkill
- dry-codingSkill
- exploratory-testSkill
- graph-think-mapSkill
- guided-codeSkill
- handoffSkill
- issue-analysisSkill
- karin-infoSkill
- local-repo-finderSkill
- milestone-triageSkill
- pr-comment-planSkill
- pr-generatorSkill
- print-debugSkill
- private-isu-tuningSkill
- property-based-testSkill
- propose-pi-extensionsSkill
- research-questionerSkill
- review-codeSkill
- skill-zipSkill
- ts-lint-searcherSkill

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:
When using skill-creator or another skill-authoring workflow, explicitly set its output directory to this checkout for standalone personal …
line 5
Very specific:
Do not copy a package between host directories or run atlantis skills sync to replicate this library.
line 13
Distinctive:
Never overwrite a locally modified install during an update.
line 18
Very specific:
Do not stage all files or publish untracked personal skills automatically.
line 21

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Skill management

This checkout owns standalone personal skills. Edit the real package here; ~/.agents/skills, ~/.codex/skills, and ~/.claude/skills are discovery paths.
When using skill-creator or another skill-authoring workflow, explicitly set its output directory to this checkout for standalone personal skills. Validate the completed package, register it with manage_skills.py register, then run check; generating files alone does not complete local registration.
Resolve an existing skill through the local manifest before updating it. Repository-scoped skills, plugin skills, and app-managed artifact templates keep their owner's prescribed location. Do not patch the bundled creator or plugin cache to impose personal placement rules.
Do not copy a package between host directories or run atlantis skills sync to replicate this library. Run python3 scripts/manage_skills.py check and python3 scripts/manage_skills.py link to inspect or create references.
External packages stay outside this repository. Use the Codex skill installer through scripts/manage_skills.py install; preserve source, ref, and license. Never overwrite a locally modified install during an update.
Skills owned by another project stay in that project, or in that project's managed install location. Do not vendor them into this standalone library.
Do not stage all files or publish untracked personal skills automatically. Review publication scope and local paths before an explicitly requested push.
Validate changes with atlantis skills check ., git diff --check, and python3 scripts/manage_skills.py check. Plugin caches and .system belong to their respective installers and are outside this library's scope.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free