My assortment of Claude Code skills
SaferSkills independently audited skills (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Lists and invokes the public skills in this repository.
| Skill | Invoke | Use when |
|---|---|---|
adversarial-reviewer | /adversarial-reviewer | Hostile bug hunt on specific code; no praise, provable failures only |
nitpicker | /nitpicker | Exhaustive whole-repo audit across code, tests, docs, config; can apply fixes |
pr-reviewer | /pr-reviewer | Review a PR or diff; outputs copy-paste markdown for GitHub PR comments |
arch-detector | /arch-detector | Detect which architectural patterns the codebase uses; writes docs/audit/arch-profile.md |
arch-auditor | /arch-auditor | Audit for architectural violations against detected or declared patterns |
doc-auditor | /doc-auditor | Verify all documentation against the codebase; find stale, missing, or incorrect docs |
security-auditor | /security-auditor | Run available security tools, parse output, write consolidated vulnerability and secret findings report |
cr-implementer | /cr-implementer | Fetch GitHub PR review comments (unresolved where available via GraphQL), evaluate, implement valid ones with validation, ask user to leave/commit/push |
claude-rules-auditor | /claude-rules-auditor | Audit .claude/rules/ files for quality, check CLAUDE.md for misplaced rules, suggest new rules from project conventions |
loophole-hunter | /loophole-hunter | Audit the Claude Code enforcement surface (rules, hooks, settings, permissions, skills) for bypassable or unenforced constraints and close them |
hooks-enforcer | /hooks-enforcer | Audit hook coverage against the project's evidence base (findings history, git, memory); find recurring failures no hook guards and context-discipline gaps; specify and wire the missing hooks in the harness's correct shape |
If the user says… → invoke this skill:
/adversarial-reviewer/nitpicker/pr-reviewer/arch-detector/arch-auditor/doc-auditor/security-auditor/cr-implementer/claude-rules-auditor/loophole-hunter/hooks-enforcer/nitpicker covers code, architecture, and docs).Run make list (or uv run scripts/list-skills.py) to print the current skill list with full descriptions, then ask the user which one fits.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.