菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.
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 | skills |
| description | 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. |
Everything public in this repository is one skill — nitpicker — invoked as
/nitpicker <command> [extra instructions]. The authoritative command table
lives in skills/nitpicker/SKILL.md (## Commands); do not duplicate it
here. /nitpicker help prints it.
If the user says… → run:
/nitpicker (default audit)/nitpicker review/nitpicker pr/nitpicker cr/nitpicker security/nitpicker tests/nitpicker types/nitpicker docs/nitpicker contributing/nitpicker arch-profile/nitpicker arch/nitpicker perf/nitpicker deps/nitpicker license/nitpicker errors/nitpicker ci/nitpicker commits/nitpicker migrations/nitpicker observability/nitpicker contract/nitpicker a11y/nitpicker privacy/nitpicker config/nitpicker iac/nitpicker prompt-safety/nitpicker leaks/nitpicker i18n/nitpicker concurrency/nitpicker agent-loopholes/nitpicker agent-hooks/nitpicker agent-rules/nitpicker complexity/nitpicker unwired/nitpicker plan/nitpicker teach/nitpicker release-gate/nitpicker baseline/nitpicker help/nitpicker default audit covers code, architecture, and docs).Run make list (or uv run scripts/list-skills.py) to print the skill and
its commands with descriptions, then ask the user which one fits.