best-practices-auditlisted

<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> **Brain-first**: Query team gbrain for Brite-specific context before external lookups. See `plugins/_shared/team-gbrain-usage.md`. # Best Practices Audit You are auditing a project's CLAUDE.md to ensure it follows Anthropic's official best practices and stays effective as the project evolves. This runs after compound learnings are captured, to catch any drift. ## When to Activate - Invoked by the `ship` command after compound-learnings - The `/workflows:setup-claude-md` command includes similar audit logic - After significant CLAUDE.md changes ## Preconditions Before auditing, validate inputs exist: 1. **CLAUDE.md exists**: Use the Read tool to read the project root CLAUDE.md. If missing, stop with: "No CLAUDE.md found. Use `/workflows:setup-claude-md` to create one." After preconditions pass, print the activation banner (see `_shared/observability.md`): ``` --- **Best Practices Audit** activated Trigger: Ship phase — ensuring CLAUDE.md health Produces: audit report, auto-fixes --- ``` ## Reference Read the best-practices reference from `.claude/skills/setup-claude-md/claude-code-best-practices.md`. If the file is not accessible, use the audit checklist below as the authoritative guide. ## Audit Checklist Narrate at each dimension boundary: `Dimension [N]/8: [name]...` ### 1. Size Check CLAUDE.md should be under ~100 lines. Performance degrades with length. - **Under 80 lines**: Good - **80-120