AI Application Audit

Iron Law: Do not auto-fix. This skill produces reports and a remediation plan — not code changes. Every finding becomes a separate task for a follow-up session.

Run a comprehensive audit of an existing agentic application or AI feature against the AI Playbook. This is for verifying existing code, not designing new features.

The audit runs in five phases with explicit confirmation gates between each. Each phase produces a written artifact in the repo. The final output is a prioritized remediation plan.

When to use this vs. the individual skills

• Use /ai-audit when you want a full pass against existing code and you're willing to let it run end-to-end.
• Use the individual skills (/ai-decision-record, /ai-launch-check, /ai-incident-response) and subagents (@ai-security-reviewer, @ai-eval-designer) when you want finer control between phases or you're only doing part of the work.

Operating procedure

Walk through the five phases below in order. Do not skip phases. Each phase has an explicit confirmation gate where the user can pause, redirect, or abort.

Before starting, load the ai-playbook skill if it isn't already in context.