Weekly Cowork System Auditor

This skill acts as an automated governance officer for your AI development environment. It conducts a comprehensive weekly audit of your Claude Projects, Cursor workspaces, or custom AI agents by analyzing project instructions, skill manifests, memory files, and automated workflows. It identifies technical debt in your prompts, outdated context, and broken automation assumptions to keep your workspace lean and efficient. As AI projects grow, “prompt rot” and context clutter often lead to assistant hallucinations or degraded performance. Prompting an AI yourself often misses the holistic view of how different instructions and skills interact. This skill provides a systematic framework to ensure your project instructions stay aligned with your 3-6 month goals, your toolset is optimized, and your persistent memory remains clean and relevant. You receive a structured System Health Report including a workspace health score, a detailed audit of existing instructions, and an actionable tracker. For environments without direct file-writing access, it generates high-quality replacement text blocks and patch instructions for you to copy-paste.