agentleFS
Sign inStart free
neko3csneko3cs/skills/AGENTS.md

skills

AGENTS.md0 starsChanged 6 days agoMITView on GitHub

The working tree is ~/.claude/skills. A save goes live across every harness immediately — before any commit, branch, or PR. Treat saving here as deploying. Every change goes through a branch and a pull request. main is protected on GitHub, so direct pushes are rejected. There is no build, no test suite, and no CI. Nothing to run. SKILL.md follows <https://agentskills.io/specification>. On top of it:

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every change goes through a branch and a pull request.

    line 7
  2. Very specific:

    Do not invent subdirectory names: Use references/ (documents), assets/ (templates, schemas, images), scripts/ (executables), even when a …

    line 18

≈ “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

neko3cs Agent Skills

What This Repo Is

The working tree is ~/.claude/skills. A save goes live across every harness immediately — before any commit, branch, or PR. Treat saving here as deploying.

Every change goes through a branch and a pull request. main is protected on GitHub, so direct pushes are rejected.

There is no build, no test suite, and no CI. Nothing to run.

Conventions

SKILL.md follows https://agentskills.io/specification. On top of it:

  • Frontmatter description is English; the SKILL.md body is Japanese.
  • description alone decides whether a skill fires, so include the phrasings a user would actually type, in both English and Japanese.
  • license: MIT on every skill.
  • Do not invent subdirectory names. Use references/ (documents), assets/ (templates, schemas, images), scripts/ (executables), even when a skill-specific name would read better. Consistency across skills beats the better name.
  • Only a skill that orchestrates other skills names them (today: resolve-issue). It names each skill it calls, because a loose hint like "implement with TDD" may not load the skill mid-task, and its house rules then drop silently. Every other skill names no caller and no peer: state the rule inline, or say the work is out of scope. This keeps dependencies one-way, so restructuring one skill never breaks another.
  • The skill list lives in README.md only. Agents receive the list from the harness, so AGENTS.md does not duplicate it. Add the README.md entry in the same commit as the skill.

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