agentleFS
TsukiNi22TsukiNi22/skills/CLAUDE.md

skills

CLAUDE.md1 starsChanged 3 days agoMITView on GitHub

Skills of the user for Claude Code (skills/<category>/<skill>/SKILL.md), the routers (skills/routers/), the tools built by setup.sh (tools/<tool>/tool.txt, ex: tools/claude-cluster) and the claude.ai packaging (claude-ai/). The global context (~/.claude/CLAUDE.md, RTK.md, hooks) lives in context/ (./setup.sh context ...). Reports of audits on this repository go in audit/ at the root; repository scripts (README tables, checks) in scripts/.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Check / fix the style with xstyle, always with --rtk (compact output made for the assistant, ~5x fewer tokens): xstyle --rtk <paths>, …

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.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
CLAUDE.md

ai-utils repository

Skills of the user for Claude Code (skills/<category>/<skill>/SKILL.md), the routers (skills/routers/), the tools built by setup.sh (tools/<tool>/tool.txt, ex: tools/claude-cluster) and the claude.ai packaging (claude-ai/). The global context (~/.claude/CLAUDE.md, RTK.md, hooks) lives in context/ (./setup.sh context ...). Reports of audits on this repository go in audit/ at the root; repository scripts (README tables, checks) in scripts/.

Checking with xstyle

  • Check / fix the style with xstyle, always with --rtk (compact output made for the assistant, ~5x fewer tokens): xstyle --rtk <paths>, xstyle --rtk --fix [CODES] <paths>, xstyle --rtk --diff (changed lines only). The human output (colors, tables, source lines) is for the user's terminal only.
  • xstyle itself lives in its own repository (TsukiNi22/xstyle, ~/personal_delivery/other/xstyle).
  • Local build of the tools (tools/claude-cluster: cmake -S tools/claude-cluster -B /tmp/cc-build, then xstyle --rtk -r tools/claude-cluster); test claude-cluster isolated with CLAUDE_CLUSTER_CONFIG_DIR, CLAUDE_CLUSTER_DATA_DIR and CLAUDE_CLUSTER_SOCKET (claude-cluster serve + the headless commands).

Writing skills

  • English, the user's style skills for the code of the scripts (python-style, coding-style for shell, cpp-style).
  • A new skill: skills/<category>/<skill>/SKILL.md with name / description frontmatter and its requires.txt, the routers that should load it, the marketplace (.claude-plugin/marketplace.json, one plugin per category folder), then python3 scripts/readme.py (writes the tables of skills/README.md and skills/<category>/README.md from the frontmatter, never edited by hand between their markers) and python3 scripts/check.py (the CI runs it too).
  • Scripts tested for real before committing (generated files, outputs), placeholders {{NAME}} in the templates.

Versions

  • The tools (claude-cluster...) follow major.minor.patch by the size of the change: a real feature (a new mode, view, subsystem: the supervisor) -> minor (1.5.0); fixes, look changes, a few settings -> patch (1.5.1); a breaking change (config / data format, a command removed) -> major. Several features in one release: one minor bump.

Git

  • Commits allowed in this repository (the user granted it), format of git-conventions (type(scope): message), ending with the Co-Authored-By trailer of the current model; never force-push or rewrite pushed history without asking.

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.