agentleFS
Sign inStart free
JeanKadangJeanKadang/DOC-GitHub-Practice-Skills/docs/claude.md

DOC-GitHub-Practice-Skills

CLAUDE.md1 starsChanged 45 days agoMITView on GitHub

Claude consumes the same canonical skills/<name>/SKILL.md files as OpenAI Codex. It ignores agents/openai.yaml; no Claude-specific policy fork exists. The installer uses -ClaudeHome when supplied. Otherwise it discovers the home from CLAUDE_HOME, then defaults to the current user's .claude directory. Skill packages are installed beneath that home's skills directory. From a trusted checkout, always preview first: Review the source, target, twelve skills, overwrite decisions, and backup paths. Then install: Upgrading over an unmodified earlier install of this package needs no -Force…

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use an explicit home for isolated testing:

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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

Claude installation

Claude consumes the same canonical skills/<name>/SKILL.md files as OpenAI Codex. It ignores agents/openai.yaml; no Claude-specific policy fork exists.

The installer uses -ClaudeHome when supplied. Otherwise it discovers the home from CLAUDE_HOME, then defaults to the current user's .claude directory. Skill packages are installed beneath that home's skills directory.

From a trusted checkout, always preview first:

pwsh -NoProfile -File .\scripts\install-skills.ps1 `
  -Target Claude -DryRun

Review the source, target, twelve skills, overwrite decisions, and backup paths. Then install:

pwsh -NoProfile -File .\scripts\install-skills.ps1 -Target Claude

Upgrading over an unmodified earlier install of this package needs no -Force and makes no backup: the installer recognizes its own marker and replaces the skill in place. Reinstalling the same release changes nothing. -Force is for a skill you changed locally (or an untracked directory): it backs the whole directory up first. Add -KeepBackups N to keep only the newest N backup sets under skill-backups. It is also what you need when you install from an unreleased main over an install of the same version: the installer then reports that the installed copy matches its own marker but differs from the source, and it cannot tell that from an edited marker.

Installed skill directories belong to the installer, which tracks them with a marker file. A file you add inside skills/<name>/ counts as a local modification: the installer refuses to reinstall that skill without -Force, and with -Force the whole directory, including your file, is backed up first. Keep personal notes outside the installed skill directories.

Use an explicit home for isolated testing:

pwsh -NoProfile -File .\scripts\install-skills.ps1 `
  -Target Claude -ClaudeHome C:\path\to\claude-home -DryRun

Restart Claude or trigger its available skill rediscovery after installation if the new skills do not appear immediately. Treat installed directories as deployment outputs and submit policy changes to this repository.

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