AI product
Prompt Audit is a Claude Code skill, also callable through the Claude API, that examines prompts, skills, and tools for outdated or conflicting practices. It identifies anti-patterns such as instructing a model to “think step by step,” unnecessary verification rituals, and contradictory rules, then removes those patterns. The videos describe it as a way to improve model performance and reduce usage costs.
1 use taken from transcripts — each links to the moment in the video.
A skill in Claude Code (run as /checkup prompt audit or via the Claude API skill) that audits your prompts, skills and tools for outdated anti-patterns like "think step by step", verification rituals and contradictory rules, and removes them — often improving performance and reducing cost.
1 in the library.