| name | ai-setup-audit |
| description | This skill should be used when the user asks to "audit my setup", "check my CLAUDE.md/AGENTS.md", "check my instruction files", "review my AI config", "clean up my instructions", "find conflicts in my setup", "optimize my agent setup", or mentions reviewing instruction files, skills folders, context files, or preferences for contradictions, redundancy, or dead weight. |
| disable-model-invocation | false |
| context | fork |
| agent | Explore |
AI Setup Audit
Read the entire setup before responding.
Scope
Check AGENTS.md, runtime-specific instruction files, every skill in the skills folder, every context-folder file, and any other instruction files found. Review every rule, instruction, and preference.
Analysis Criteria
For each rule, instruction, or preference, evaluate:
- Already default? — Is this something the AI Assistant already does by default without being told?
- Conflicts? — Does this conflict with another rule elsewhere in the setup?
- Redundant? — Does this repeat something that's already covered by a different rule or file?
- Reactive patch? — Does this target one specific bad output rather than improve outputs overall?
- Too vague? — Is this so vague that it would be interpreted differently every time? (e.g., "be more natural" or "use a good tone")
Output Format
Provide:
- A list of everything to cut, with a one-line reason for each
- A list of any conflicts found between files
- A cleaned up version of AGENTS.md with the dead weight removed
