Menu
Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Hostile audit toolkit: one entry point dispatching specialist commands — adversarial review, security, tests, docs, architecture, performance, dependencies, error handling, CI, commits, migrations, observability, API contracts, a11y, privacy, config, resource leaks, i18n, concurrency, unwired code, PR review and review-comment implementation. Use when auditing or reviewing a repository, PR, or any quality dimension of a codebase — "audit this", "review the whole codebase", "find all problems", "exhaustive review", "/nitpicker <command>", a release gate check, or any specific audit ask (security scan, find race conditions, audit the tests, review the PR, fix the CR comments).
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Routes audit requests to the right /nitpicker command. Use when the user wants to run one of the hostile audit commands in this repo, or asks what audit commands are available.
Use when creating a new hostile audit command for the nitpicker skill in this repository.
Use when validating that all changes in the current branch are ready to be included in a release PR managed by release-please automation.
Use when verifying that a skill actually changes Claude's behaviour — runs TDD pressure scenarios against a skill before and after writing it.
| name | validate-skills |
| description | Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill. |
Run the validator across all skills — public and internal:
uv run scripts/validate-skill.py
uv run scripts/validate-skill.py .claude/skills/*/SKILL.md
To validate only public skills:
uv run scripts/validate-skill.py
To validate only internal skills:
uv run scripts/validate-skill.py .claude/skills/*/SKILL.md
If any errors are reported, fix them before proceeding. Errors are blocking.
Warnings should be reviewed; fix if the skill is being released.
Run the version sync check:
uv run scripts/check-version-sync.py
If all checks pass, skills are release-ready.
| Check | Level |
|---|---|
| Frontmatter present | Error |
name field present | Error |
description field present | Error |
| Description contains "Use when" trigger clause | Error |
| Description ≤ 1024 chars | Error |
| Skill name matches directory name | Error |
| Header level progression (no skipping levels) | Error |
Description with ': ' must be single-quoted | Error |
Command tables (## Commands, ## Internal commands) ↔ commands/*.md files 1:1 (skills with a commands/ dir) | Error |
| Duplicate headers within a SKILL.md body | Error |
Command file h1 is # /<skill> <command> — … | Error |
Command file has ## When to use | Error |
| Command file header level progression | Error |
Legacy output paths (./codereview.md etc.) | Warning |
| Body exceeds 500 lines | Warning |