Tidy Skill
Read-only hygiene audits that stop agents littering repos with plan.md/todo.md junk.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 18, 2026 · e4bb213
Ran score_repo_hygiene.py on a throwaway repo with plan.md/todo.md/summary.md in root — it returned a real 57/100 'Needs tidy-up' score with a dimension breakdown and named the 3 suspicious files, something a baseline answer only eyeballs.
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 Tidy Skill does
Governs where AI-agent-created files (plans, todos, reports, caches) are allowed to live, and scores a repo's artifact hygiene with a real Python/PowerShell scanner. Triggers on repo cleanup, hygiene scoring, workspace cache audits, and WSL2/Docker/C-drive growth questions; stays out of source code and tool-state directories.
How to install Tidy Skill
git clone https://github.com/Phoenix0531-sudo/tidy-skill
mkdir -p ~/.claude/skills
cp -r tidy-skill/skills/tidy-skill ~/.claude/skills/tidy-skill
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Tidy Skill
-
/tidy-skillRead-only hygiene audits that stop agents littering repos with plan.md/todo.md junk.
It also activates on plain-language prompts like these:
-
scan my repo root for stray plan.md and todo.md files agents left -
score how tidy my workspace is before I hand it to a teammate -
why is my WSL2 disk filling up with cache junk from agents?
Frequently asked questions
- Is the Tidy Skill skill free?
- Yes. The skill itself is free from Phoenix0531-sudo/tidy-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Tidy Skill work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran score_repo_hygiene.py on a throwaway repo with plan.md/todo.md/summary.md in root — it returned a real 57/100 'Needs tidy-up' score with a dimension breakdown and named the 3 suspicious files, something a baseline answer only eyeballs.
- What is the Tidy Skill 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 Tidy Skill?
- 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 Tidy Skill 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.