What problem does it solve?
Manually tracking the quality, relevance, and redundancy of a growing collection of custom Claude skills and commands is time-consuming and error-prone, especially for users managing dozens of AI-powered workflow tools.
Core Features & Use Cases
- Dual Audit Modes: Run a fast Quick Scan to re-evaluate only recently changed skills (5–10 minutes) or a Full Stocktake for a complete review of all global and project-level skills (20–30 minutes).
- Structured Quality Evaluation: Uses a standardized checklist to assess content overlap, technical currency, usage frequency, and uniqueness, generating actionable verdicts (Keep, Improve, Update, Retire, Merge) for each skill.
- Result Caching: Automatically saves evaluation results to avoid redundant rework, only re-evaluating skills that have changed since the last run.
- Use Case: If you manage a library of 30+ custom Claude skills for your team or personal workflow, use this skill to identify outdated or redundant skills, reduce maintenance overhead, and ensure your AI tooling stays aligned with current needs.
Quick Start
Ask the skill-stocktake skill to run a full audit of all your global and project-level Claude skills and return a prioritized list of skills to keep, improve, update, retire, or merge.
