audit
免费Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.
中文简介正在准备中。当前显示原文说明。
Deep code review with web research. Use when double-checking code against latest docs, verifying dependency versions, or reviewing security concerns. Complements automatic quality hook with ecosystem verification.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Deep review with web research to verify against current ecosystem. Complements automatic hook.
When to use this skill (not automatic hook):
Relationship: Automatic hook does fast check with existing knowledge. This skill does deep dive with web research (2-3 min).
If in BDD workflow, read current ticket from .safeword-project/tickets/ and apply phase-appropriate research:
| Phase | Research Focus |
|---|---|
| intake | Similar features in ecosystem, scope patterns |
| define-behavior | Testing patterns, BDD research and patterns |
| scenario-gate | Architecture patterns, test layer strategy |
| implement | Library versions, deprecated APIs, security |
| done | CI/CD patterns, release checklists |
CRITICAL: This is your main differentiator from automatic hook.
Search for: "[library name] latest stable version 2025" Search for: "[library name] security vulnerabilities"
Flag if outdated:
Fetch official documentation for libraries in use.
Look for:
## Quality Review
**Versions:** [✓/⚠️/❌] [Latest version check]
**Documentation:** [✓/⚠️/❌] [Current docs check]
**Security:** [✓/⚠️/❌] [Vulnerability check]
**Verdict:** [APPROVE / REQUEST CHANGES / NEEDS DISCUSSION]
**Critical issues:** [List or "None"]
**Suggested improvements:** [List or "None"]
**Provenance:** For version/API claims:
- (verified: [source URL or doc title]) — fetched this session
- (training data: may be outdated) — not verified
- (uncertain) — could not verify
**Next:** [concrete action — upgrade X from a.b.c to x.y.z, refactor {file}:{line}, ask team about Z, or proceed to implementation if APPROVE]
The **Next:** line is required. On APPROVE, name what to do now (proceed, commit, run /verify). On REQUEST CHANGES, name the specific edit and re-review trigger. On NEEDS DISCUSSION, name the question to ask. A verdict that doesn't tell the reader what to do next is incomplete.
Voice: plainspoken and concise — write to be scanned.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.
中文简介正在准备中。当前显示原文说明。
Behavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner.
中文简介正在准备中。当前显示原文说明。
Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.
中文简介正在准备中。当前显示原文说明。
Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
中文简介正在准备中。当前显示原文说明。
Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.
中文简介正在准备中。当前显示原文说明。