agentsclimarketplace

Skill doctor

Skill KyTiXo/skill-doctor

Audit a skill against Pocock's write-a-skill spec and return a prioritized, diagnose-only fix report.From its SKILL.md

Install
npx -y skills add KyTiXo/skill-doctor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 547 tokens by cl100k_base, as published. Nobody here has run it

Skill Doctor

Audits a skill against Matt Pocock's write-a-skill (the enforced Review Checklist) and writing-great-skills (the deeper principles). Diagnose-first — the two gates below never move.

🔒 Two gates (never cross)

  1. Diagnose — once the target skill is picked, only read and produce a report. Change nothing.
  2. Refactor — after the report, wait for an explicit "go fix it" before editing. A report is not consent.

Refactoring touches only the target skill's own directory. Never other files, never user data.

Flow

  1. Read the target SKILL.md in full, plus any linked references/.
  2. Score it against every row in references/checklist.md — five sections: Invocation, Structure, Steps, Pruning, Hygiene.
  3. Write the gate-1 report via references/report-template.md (content only). Exception: user said with tags or include meta-params upfront → also fill references/meta-params-template.md in the report (propose only, no writes).
  4. Stop at gate 1 — change nothing.

The five checks

Invocation · Structure · Steps · Pruning · Hygiene. Full criteria live in references/checklist.md — score every row from that file, never from memory.

Failure-mode lookup

Name the smell when you find it: premature completion, duplication, sediment, sprawl, no-op, blind-guess. Tell + first fix for each: references/checklist.md § Failure-mode lookup.

Refactor (only after gate 2)

Back up first: cp SKILL.md SKILL.md.bak-<date>. Then apply the report's prioritized fix list in order. Re-check the line count and grep the leading words to confirm nothing got lost in the move.

Meta-params pass (opt-in — default after gate 2)

Run only on explicit request. Default timing: after content refactor. Upfront exception: with tags / include meta-params in the audit invocation → proposals in gate-1 report.

Propose via references/meta-params-template.md + references/optimize-tags.md. Nothing writes until the user consents — bulk (apply the tags) or cherry-pick (name the rows). Run each validation test before writing; skip or revert on request. Never mix tag writes into the content refactor unless the same message explicitly approves both.

What ships with it: 10 files

3525.3 KB alongside SKILL.md, 1 of them executable

images/

scripts/

Keep looking

Skills are one crate of 326,645. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.