/audit-claude-md
Audit all CLAUDE.md files in the current project for staleness and coverage gaps. For each existing file, scores freshness by checking git churn in its scoped directory since the file was last touched; flags content drift for stale ones; discovers directories that should have a
$ npx -y skills add ada-ggf25/AI-Tools --skill audit-claude-md --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/audit-claude-md
Context preview
The summary Claude sees to decide when to auto-load this skill.
Audit all CLAUDE.md files in the current project for staleness and coverage gaps. For each existing file, scores freshness by checking git churn in its scoped directory since the file was last touched; flags content drift for stale ones; discovers directories that should have a
Global Claude Code and Codex skills/agents, versioned in one place so they stay in sync across devices.
Other skills on ai-tools.
- /codex-to-claude
Scans global/codex/skills/ and global/codex/agents/ for items missing from global/claude/skills/ and global/claude/agents/, presents the gap list for approval, then adapts each approved item to Claude Code format and writes it to the global/claude/ directory, then runs
Open skill - /agents-to-claude-md
Scans the current repo for AGENTS.md files, finds directories that lack a matching CLAUDE.md, translates each AGENTS.md to a CLAUDE.md draft (applying the Codex→Claude substitution table), runs a /where-claude sanity check per candidate, and — with per-item approval — either
Open skill - /audit-docs
Audit hand-authored project documentation (.md, .txt, .rst, .adoc) for accuracy against the codebase as ground truth. Extracts verifiable claims from each doc (code blocks, shell commands, file paths, version/dependency refs, symbol names), checks them against actual code and
Open skill - /bootstrap-project
One-command new-repo setup orchestrator. Detects the stack, then runs the project-setup workflow end to end - root CLAUDE.md (/init), nested CLAUDE.md placement (/where-claude), scoped permissions (/setup-permissions), an automation proposal (propose-automation), and a couple of
Open skill - /commit
Create a git commit following the Conventional Commits specification (conventionalcommits.org). Reads the diff, auto-infers scope from file paths, proposes type + scope + description + body, and shows the message for approval before committing. Supports optional push, language
Open skill - /debate
Spawn Claude sub-agents to debate a topic, idea, proposal, or decision from multiple perspectives. A Proponent argues for it, a Critic argues against, an optional Devil's Advocate challenges both, and a Synthesizer produces a structured verdict. Use when you want rigorous
Open skill