Two prompt audits worth running on your Claude Code setup
RLanceMartin · x · 2026-11-15
petergyang shares two handy prompts for Claude Code with Fable 5.2 / Opus 5.5:
- /doctor prompt-audit: audits your whole setup (CLAUDE.md, skills, commands) and proposes fixes — the screenshot shows it spinning up 5 parallel reviewers to cover 65 user skills and 60 plugin skills.
- /claude-api prompt-audit [skill name]: deep-audits a single skill.
He also links a tutorial covering how he splits real work across models in 5 use cases (inbox chief-of-staff, career advice, podcast production automation, fitness app building, and more), and wishes Claude Code would auto-suggest these audits whenever Anthropic ships a new model.
More from coding & agent
- Weekend reads: HF decision models, llama.cpp 1.0, 3D fine-tuning guide and more — kalyan_kpl · 2026-11-15
- Dev ditches Linear for Flywheel, a graph-based tool for mapping SWE decisions — tensorqt · 2026-11-15
- Where should agent instrumentation end? Devs weigh 3 designs for verifying external state — Sensitive-Parsnip-12 · 2026-11-15
- Solo founder claims $6,000 in a week running an internet business with a team of AI agents — CustomerFearless2294 · 2026-11-15
- Gemini CLI docs PR fixes stale Zed flag and wrong ACP expansion in CLI reference — DZH166 · 2026-11-15
- Two AI agent teams given $150 in DoorDash credits compete to decorate booth at Takeoff DC — lfschiavo · 2026-11-15