command-surface-audit
Skill9 starsChanged 5 months agoMITView on GitHub
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.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to build an evidence-backed command matrix from the current checkout.
- Distinctive: line 14
Run safe commands. Use dry-run or check mode for packaging and release paths.
- Distinctive: line 15
Do not run publish/write commands without explicit user confirmation.
- Very specific: line 21
Write _workspace/quality-audit/command-surface-{N}.md:
- Very specific: line 34
When running locally from Codex, use rtk proxy <command> for raw commands.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ableton-mind-buildSkill
- ableton-remote-scriptSkill
- cross-boundary-qaSkill
- device-schema-extractionSkill
- mcp-distributionSkill
- mcp-server-developmentSkill
- recipe-authoringSkill
- ableton-mind-buildSkill
- ableton-mind-quality-auditSkill
- ableton-remote-scriptSkill
- cross-boundary-qaSkill
- device-schema-extractionSkill
- local-copilotSkill
- mcp-distributionSkill
- mcp-server-developmentSkill
- recipe-authoringSkill
- refactor-maintainabilitySkill
- runtime-release-auditSkill
- security-auditSkill
- test-coverage-expansionSkill
- usability-flow-auditSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.