agentleFS
shivae372shivae372/claude-bootstrap/.claude/skills/doctor/SKILL.md

doctor

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Self-heals this project's Claude Code setup. Diagnoses broken or missing pieces — skills with no SKILL.md, hooks referenced but absent or non-executable, invalid settings.json, bloated CLAUDE.md — scores health, and applies safe fixes. Use when something in the setup seems off, after edits to .claude/, when a hook or skill isn't firing, or on a `[heal]` nudge. Triggers: 'is my setup ok', 'fix my claude setup', 'why isn't my skill/hook working', '/doctor'.

85 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use uninstall, cancel and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    uninstall

    Uninstall a community skill that was installed via the hub. Confirms before deleting files, refuses to touch first-party plugin skills, and logs every action. Use when the user wants to fully remove a community skill ("uninstall [skill]", "remove this skill") rather than just disable it.

    Also in 6 projects that use this

  • woosikkimSkill

    cancel

    Clear any stale OMC-Slim state

    Also in 3 projects that use this

  • ibahgatSkill

    mode

    Inspect or switch omi operating mode/profile for speed, depth, autonomy, or strict quality gates.

    Also in 3 projects that use this

  • BlockSkill

    open

    Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.

    Also in 3 projects that use this

  • QinghongLinSkill

    editor

    Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 15 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 64 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Keep the setup healthy without the user having to understand its internals.

    line 8
  2. Distinctive:

    If a finding's root cause is ambiguous, show the user the finding and the proposed fix before applying it.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “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

Purpose

Keep the setup healthy without the user having to understand its internals. The diagnosis is fully deterministic (no guessing); repairs are explicit and safe.

When to use this

  • A hook/skill/command isn't behaving, or the user edited .claude/ by hand.
  • A [heal] nudge appeared (a tool failed repeatedly — see .claude/state/failures.jsonl).
  • Proactively after augment/forge writes new config.

Steps

1. Diagnose

python3 .claude/engine/doctor.py --json

Returns {score, errors, warnings, findings[]}. Each finding has where, problem, fix, and auto_fixable.

2. Apply the safe auto-fixes

python3 .claude/engine/doctor.py --apply

This performs only non-destructive repairs (e.g. chmod +x hooks). Everything else is left to you with a precise fix string.

3. Repair the rest, in order of severity

  • error first (a missing hook reference, a skill with no SKILL.md, invalid JSON). Fix the root cause: restore/author the file, correct the JSON, or remove the dead reference. For a skill dir missing SKILL.md, use forge (or delete it if obsolete).
  • warn next (non-executable hook already covered by --apply; oversized CLAUDE.md → trim and move detail into skills; agent missing frontmatter → add it).
  • info as time allows.

4. Re-check and learn

Re-run the diagnosis until errors: 0. If a failure pattern recurs, record it so the setup avoids it next time:

echo '{"category":"fix","text":"<what was broken> → <how fixed>","tags":["heal"]}' \
  | python3 .claude/engine/learn.py add

Output

A health score and a clean before/after: what was broken, what was auto-fixed, what you repaired, ending at 0 errors.

Guardrails

  • Auto-fix is safe-only; never delete user content to "fix" a finding without asking.
  • If a finding's root cause is ambiguous, show the user the finding and the proposed fix before applying it.

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.