Doc Cleanup

Two-pass Markdown rot audit: evidence-backed diagnosis, edits only on approval

Tested · Works

Test report

Verdict
Tested · Works
Score
9.6/10
Tested
Aug 10, 2026
Environment
Claude Code 2.x (agent harness)

Pointed it at a live Astro catalog repo's entry docs and docs/ folder. Without the skill I produced four impressions ("numbers look stale", "there's a duplicate protocol file"); with it, thirteen findings that each survived an executed check — README claims 64 skills where skills.json holds 2433, claims 12 categories in one paragraph and 8 in another, and its launch checklist still tells you to wire up a newsletter endpoint, swap a mailto buy button for Gumroad and generate an OG image that all shipped long ago. The single worst hit it caught is a README line asserting the test data is sample material, contradicted by 1320 pass / 715 setup / 290 queue / 108 fails verdicts in the dataset. It also flagged an orphan docs-internal-test-protocol.md — 56 lines diverged from the live protocol, zero inbound references — that omits the security gate and tells an agent to grade installs by fetching files instead of running them. Pure Markdown, no scripts, and the diagnostic pass genuinely left the worktree untouched.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 9/10
  • Docs & honesty 5/5

What Doc Cleanup does

Audits a repository's Markdown for context rot — finished checklists still written as instructions, shipped plans still written as intent, stale counts, dead paths and contradicting sources of truth — and requires repository evidence for every finding before proposing a fix. Runs diagnose-and-report first and stops for approval, then executes with an archive-and-rewrite playbook and a link/diff verification pass. Triggers on requests to review, clean or fact-check project docs, CLAUDE.md or AGENTS.md.

How to install Doc Cleanup

git clone https://github.com/aka-luan/doc-cleanup.git
mkdir -p ~/.claude/skills
cd doc-cleanup && cp -r skills/doc-cleanup ~/.claude/skills/doc-cleanup

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Doc Cleanup

  • /doc-cleanup Two-pass Markdown rot audit: evidence-backed diagnosis, edits only on approval

It also activates on plain-language prompts like these:

  • Audit our docs folder for stale instructions and dead paths
  • Check README.md for finished checklists still written as todos
  • Find contradicting sources of truth across our markdown docs

Frequently asked questions

Is the Doc Cleanup skill free?
Yes. The skill itself is free from aka-luan/doc-cleanup. SkillProof publishes the install command and an independent test verdict at no cost.
Does Doc Cleanup work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Aug 10, 2026. Verdict: Tested · Works. Pointed it at a live Astro catalog repo's entry docs and docs/ folder. Without the skill I produced four impressions ("numbers look stale", "there's a duplicate protocol file"); with it, thirteen findings that each survived an executed check — README claims 64 skills where skills.json holds 2433, claims 12 categories in one paragraph and 8 in another, and its launch checklist still tells you to wire up a newsletter endpoint, swap a mailto buy button for Gumroad and generate an OG image that all shipped long ago. The single worst hit it caught is a README line asserting the test data is sample material, contradicted by 1320 pass / 715 setup / 290 queue / 108 fails verdicts in the dataset. It also flagged an orphan docs-internal-test-protocol.md — 56 lines diverged from the live protocol, zero inbound references — that omits the security gate and tells an agent to grade installs by fetching files instead of running them. Pure Markdown, no scripts, and the diagnostic pass genuinely left the worktree untouched.
What is the Doc Cleanup SkillProof Score?
9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Doc Cleanup?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Doc Cleanup with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.