{"version":"2.1.283","anchor":"doctor-prompt-audit-runs-the-claude-api-skills-prompt-au","canonical_anchor":"doctor-prompt-audit-runs-the-claude-api-skills-prompt-au","heading":"\/doctor prompt-audit reviews your project's instruction files","tier":"use","area":"Slash Commands","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283\/e\/doctor-prompt-audit-runs-the-claude-api-skills-prompt-au","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283","markdown":"### `\/doctor prompt-audit` reviews your project's instruction files\n\n`\/doctor prompt-audit` hands off to the bundled claude-api skill to audit CLAUDE.md, rules, skills and other instruction files\n\n**Unclear.** What the optional path after `prompt-audit` changes is not stated.\n\n**What**\n\n`\/doctor` now accepts `prompt-audit`, optionally followed by a path. With it, `\/doctor` hands off to the prompt audit in the bundled claude-api skill. A skill is a packaged set of instructions Claude Code can use. The audit covers your project's instruction files:\n\n- `CLAUDE.md` and `AGENTS.md`\n\n- rules, skills, commands and agents\n\n- output styles\n\nIt is told not to read settings files, `.mcp.json` or `~\/.claude.json`, because those are not instructions and can hold secrets. If the claude-api skill is unavailable, the model explains why and stops. It can be unavailable because it is disabled, set to off in `skillOverrides`, or turned off with all bundled skills by `disableBundledSkills` or `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS`. Before this, `\/doctor` only took free-form extra instructions.\n\n**Why**\n\nIt gives you an easy way to have the instruction files Claude reads reviewed, without exposing configuration files that may hold secrets.\n\n- Area: Slash Commands\n- Names: `\/doctor prompt-audit`\n- Tier: Use it now\n- Useful: 5\/5\n- Signal: 2\/5"}