USE WHEN inheriting a legacy repo, when user asks "what's missing for AI-first work here?", "is this repo agent-ready?", "audit my repo", "is anything out of sync with the code?", or when the bare-repo-nudge / cheatsheet hook suggests a checkup. Read-only AI-readiness audit — scores ~20 dimensions across Foundation (AGENTS.md / CLAUDE.md / per-dir AGENTS.md), Why (ADRs + session logs), What (GLOSSARY.md + architecture.yml), In-code (AIDEV anchor density + overdue), Hygiene (tests, LOC ratio, structured logging, .gitignore, README, manifest), AND Sync (code↔docs drift: arch-map vs disk, glossary vs code, per-dir AGENTS.md vs dir activity, CHANGELOG vs version, README slash-refs). Each gap → concrete fix action. Differentiated from /init-repo (one-shot bootstrap, writes files) and /stack-check (time-based freshness) — this skill answers completeness AND drift in one pass. See ADR 0006 (initial design) and ADR 0007 (Sync addition) for rationale.
$npx -y skills add filip-podstavec/claude-leverage --skill repo-doctorInstalls into the current project.
Run `npx skills use "https://github.com/filip-podstavec/claude-leverage" --skill "filip-podstavec/claude-leverage/repo-doctor"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/filip-podstavec/claude-leverage" that are relevant to the current task. Run `npx skills add "https://github.com/filip-podstavec/claude-leverage"` and select the relevant skills, then follow their instructions.