ai-ready

Score a codebase for AI-readiness against a 7-category 100-point rubric and generate a markdown report, an HTML dashboard, module-level CLAUDE.md scaffolds, and an ANTIPATTERNS.md seed extracted from git history. Use this skill whenever the user wants to assess how well their codebase is set up for AI agents (Claude/Codex/Gemini), generate per-module CLAUDE.md files, extract anti-patterns, or build a navigation map for a large codebase — even if they don't explicitly say the word "audit". Trigger on phrases like "ai-ready audit", "AI 준비도", "코드베이스 감사", "score my codebase for AI agents", "generate module CLAUDE.md", "anti-patterns from git history", "AI 친화 코드베이스", "make this repo navigable for Claude", or "we have no map for AI".

Apply ROI-prioritized actions from an ai-ready:audit run. Read `<target>/.ai-ready/audit.json` + `audit-report.md`, then for each top-N action either run a mechanical script (CLAUDE.md scaffolds, ANTIPATTERNS seed, INDEX.md, ARCHITECTURE.md Mermaid diagrams, freshness Stop hook install, naming/testing extraction) or apply a judgment-based change via Claude (anti-pattern entries, ADRs, "DO NOT" sections, "When to use" guides). Use this skill after the user has run ai-ready:audit and now wants to actually execute the recommended improvements rather than just read the report — invoke it whenever they say "apply the audit", "audit 적용", "ROI 액션 실행", "우선순위 액션 적용", "AI 준비도 개선 실행", "audit fix", or refer to running through the action list, even casually.