Command surface audit
Skill Pantani/ableton-mind/.claude/skills/command-surface-audit
Audit, classify and run the real ableton-mind command surface. Use whenever package scripts, CI commands, docs commands, bins, "run all commands", stale scripts, broken commands or command coverage are mentioned.From its SKILL.md
npx -y skills add Pantani/ableton-mind --skill command-surface-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 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
1.4 KB, as published. Nobody here has run it
Command Surface Audit
Use this skill to build an evidence-backed command matrix from the current checkout.
Workflow
- Inventory commands from package.json scripts, bin entries, .github/workflows, docs snippets and scripts/.
- Classify each command as safe read/check, local mutating, external read, publish/write or hardware/live.
- Run safe commands. Use dry-run or check mode for packaging and release paths.
- Do not run publish/write commands without explicit user confirmation.
- Record exact failures with the command, output signature, source file and likely owner.
- Flag commands that exist in docs but not package.json, or package scripts that no workflow/docs can reach.
Report Format
Write _workspace/quality-audit/command-surface-{N}.md:
| Command | Source | Class | Status | Evidence | Notes |
|---|
End with:
- Broken commands.
- Stale or undocumented commands.
- Commands blocked by missing Live, hardware, credentials or external services.
- Suggested tests or docs changes.
Local Execution
When running locally from Codex, use rtk proxy <command> for raw commands. Keep raw command names in the report so CI/users can copy them.