claude-auditlisted

Audit a project's effective Claude Code configuration — custom and plugin-provided agents and skills — and produce a structured overlap/conflict report with keep / modify / drop recommendations scoped to the project's stated objectives. Trigger this skill whenever the user types `/claude-audit`, asks to "audit my claude config", "find overlap in my agents", "check for skill conflicts", "are any of my agents duplicates", "what's redundant in my setup", or any similar request to review the agent/skill surface for the current project. Also trigger after a fresh plugin install when the user wants to verify nothing new collides with what's already there.
glitchwerks/claude-prospector · ★ 1 · AI & Automation · score 70

Install: claude install-skill glitchwerks/claude-prospector

# Claude Audit Skill Produce a deterministic overlap/conflict report for the project's effective Claude Code configuration. The audit considers user-scope (`~/.claude/`), project-scope (`<project>/.claude/`), and plugin-provided sources together — because that is what the agent actually loads at runtime. The output is a single markdown report. The skill itself does **not** modify any files. All recommendations are presented to the user; they decide what to change. --- ## Step 1: Discover the project objective Before evaluating overlaps, read the project's `CLAUDE.md` (and any `README.md`) at the repo root to understand what the project does. Specific things to extract: - **Domain** — web app, infra, mobile, ML, mod development, etc. - **Languages / frameworks** — informs which language skills are relevant - **Workflows codified in CLAUDE.md** — issue tracking, PR conventions, branching, testing Recommendations later are scoped to these. A `python` skill is not "redundant" just because the project also uses TypeScript — it might still be load-bearing for tooling scripts. If no project-level `CLAUDE.md` exists, fall back to the user-level `~/.claude/CLAUDE.md` and note that the audit is using the user-scope objective only. --- ## Steps 2–5: Deterministic inventory and analysis Run the built-in CLI subcommand and capture its markdown output: ```bash python -m claude_prospector audit --project-dir <project-root> ``` This single command covers all four deterministic s