Prompt audit with Opus 5.5 surfaces ~70 fixes for your Claude Code skills and CLAUDE.md
daniel_mac8 · x · 2026-09-24
Developer danielmac8 shares a workflow (originally from @RLanceMartin): run '/claude-api prompt-audit' in Claude Code to have Opus 5.5 audit your skills, CLAUDE.md, and AGENTS.md.
The audit reportedly found about 70 improvements, mainly removing anti-patterns in instructions that restrict Opus 5.5's performance. The whole process takes roughly 5 minutes, making it a quick, actionable way for Claude Code users to clean up their agent config files.
Related event: One command audits your Claude Code config for anti-patterns(3 posts)→
More from coding & agent
- Plurai launches free agent simulation testing inside Claude Code and Cursor — PrajwalTomar_ · 2026-11-11
- AI-built game nerfed 40% after Claude playtest bot beat it in 6 minutes — builderjaydub · 2026-11-11
- Anthropic launches Claude Tag for Slack, claims 65% of its product code is AI-written — nikola_mr64990 · 2026-11-11
- The key to expert-driven evals: maximize information gain per unit of expert attention — danshipper · 2026-11-11
- Aqua launches Notetaker: meeting notes piped to AI agents via MCP — Scobleizer · 2026-11-11
- KAIST's WikiTrace: evidence-linked memory fixes agent "memory-induced degradation" — dair_ai · 2026-11-11