There is this useful command in Claude Code "/claude-api prompt-audit" which analyzes your prompts, CLAUDE.md, skills etc. and recommends how to rewrite some of them for new model to digest better. Don't be missled by 'claude-api' part in the command, it works for all type of projects.

Update as of October 3, 2026.

Also new command has been introduced in 2.1.283 Claude Code version for prompt auditing to examine CLAUDE.md, skills, agents, commands for prompting patterns written for older Claude generations:

/doctor prompt-audit <path>

or its alias

/checkup prompt-audit <path>