AgentStack
SKILL verified MIT Self-run

Skill Doctor

skill-kytixo-skill-doctor-skill-doctor · by KyTiXo

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

No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-kytixo-skill-doctor-skill-doctor

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Skill Doctor? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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).

  1. 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-. 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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.