bs-claudemd
100 / 100 · Low risk
Fine to try.
Audit a CLAUDE.md for cruft and render a light-theme report website. Reads the file line by line and flags vague rules with no checkable criterion, low-signal lines that only restate what the model already does, overlapping rules said more than once, and internal contradictions, then scores the file with a BS-o-meter and grade. Can also diff two CLAUDE.md files and flag rules that tell the model opposite things. Use when the user runs /bs-claudemd or asks to review, audit, grade, lint, or clean…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'bs-claudemd' ] || [ -L ~/.agents/skills/'bs-claudemd' ]; then echo 'A skill folder named bs-claudemd already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/diegopacheco/ai-playground' "$d" && git -C "$d" checkout --quiet 'd9a66a7614b743615074ea74689ae2039fadcb2d' -- 'pocs/agent-skill-claudemd-bs/skill' && mkdir -p ~/.agents/skills && cp -R "$d"/'pocs/agent-skill-claudemd-bs/skill' ~/.agents/skills/'bs-claudemd' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'bs-claudemd' ~/.claude/skills/'bs-claudemd' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/diegopacheco/ai-playground/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | d9a66a7 | 100 |