agentleFS
YIMO691YIMO691/claude-skills-kit/.claude/skills/claude-config-maintainer/SKILL.md

claude-config-maintainer

Skill0 starsChanged 6 months agoMITView on GitHub

维护 Claude/Codex 配置仓库。Use when updating reusable CLAUDE.md, AGENTS.md, .claude/rules, .claude/skills, agents, commands, install scripts, or extracting project-specific rules into a reusable GitHub-hosted configuration kit.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep universal instructions in CLAUDE.md, AGENTS.md, and .claude/rules/.

    line 11
  2. Very specific:

    Put reusable workflows in .claude/skills/<skill-name>/SKILL.md.

    line 12
  3. Very specific:

    Keep each SKILL.md short; move long examples or templates to docs/ or skill references.

    line 13
  4. Very specific:

    Update docs/reference/skills-manifest.md when adding, renaming, or deleting skills.

    line 14
  5. Very specific:

    Test scripts/install-claude-kit.ps1 after structural changes.

    line 15
  6. Distinctive:

    Keep: workflow, safety constraints, validation habits, file placement logic, reusable templates.

    line 19
  7. Distinctive:

    Remove: API keys, tokens, account IDs, private URLs, temporary logs, generated caches.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
SKILL.md

Claude Config Maintainer

Workflow

  1. Separate universal rules from project-specific facts.
  2. Keep universal instructions in CLAUDE.md, AGENTS.md, and .claude/rules/.
  3. Put reusable workflows in .claude/skills/<skill-name>/SKILL.md.
  4. Keep each SKILL.md short; move long examples or templates to docs/ or skill references.
  5. Update docs/reference/skills-manifest.md when adding, renaming, or deleting skills.
  6. Test scripts/install-claude-kit.ps1 after structural changes.

Extraction Rules

  • Keep: workflow, safety constraints, validation habits, file placement logic, reusable templates.
  • Generalize: project paths, milestone names, private process details, local machine paths.
  • Remove: API keys, tokens, account IDs, private URLs, temporary logs, generated caches.
  • Mark optional stacks, such as Unity, as profiles instead of forcing them into every project.

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.