generic-audit
通用代码审计 — 自动对比 plan/PRD 与实际代码实现，检查质量、安全、一致性。适用于任何语言和框架。
Skill by Brothelmdzz
Chalk Labs
Need help deploying generic-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/brothelmdzz-generic-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/generic-audit
What's inside
- Skill name
generic-audit- Description
- 通用代码审计 — 自动对比 plan/PRD 与实际代码实现，检查质量、安全、一致性。适用于任何语言和框架。
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- report-template.md
SKILL.md (first lines)
# 通用代码审计
## 约束
- 必须对比 plan/PRD 与实际代码，不凭印象审计
- HIGH 问题必须自动修复后重编译验证
- 报告必须非空（>500 字节 + 至少 2 个 ## 标题），否则 stop-hook 打回
## 审计维度
| 维度 | 检查内容 | 严重级别 |
|------|---------|---------|
| 需求覆盖 | plan 中每个变更点是否都已实现 | HIGH |
| 代码质量 | 空指针、资源泄露、异常处理、边界条件 | MEDIUM-HIGH |
| 安全性 | SQL 注入、XSS、敏感信息泄露、权限校验 | HIGH |
| 错误处理 | 异常是否正确捕获和上报 | MEDIUM |
| 一致性 | 命名规范、代码风格、项目约定 | LOW |
## 参考
- 报告格式 → 读取 report-template.md
## 产出
`.claude/reports/audit-{module}-{date}.md`（格式见 report-template.md）。From Brothelmdzz/dev-harness, MIT.
More from Brothelmdzz/dev-harness
- 0.501score
generic-tdd
Brothelmdzz
TDD 模式实现 — RED-GREEN-REFACTOR 循环，先写测试再写代码。与 implement 阶段集成，强制测试优先。
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
generic-test
Brothelmdzz
通用测试执行 — 自动检测项目测试框架，运行测试，验证功能正确性。支持 pytest/jest/gradle/cargo 等。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-frontend-implement
Brothelmdzz
通用前端实现 — 检测前端技术栈，按 plan 逐 Phase 实现组件/页面/路由变更，自动门禁验证。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-frontend-research
Brothelmdzz
通用前端代码库研究 — 并行 subagent 扫描前端代码结构，产出结构化研究报告。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-implement
Brothelmdzz
通用计划执行 — 按 plan 文档逐 Phase 实现代码变更，自动门禁验证。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-research
Brothelmdzz
通用代码库研究 — 并行 subagent 扫描代码库，产出结构化研究报告。适用于任何项目。
SkillCFreshness: C★ 2Claude Code +9 - 0.497score
generic-review
Brothelmdzz
通用代码审查 — Claude 内部三路并行（code + security + arch）+ 可选第四路跨厂商对抗审查（codex cli），汇总对比。
SkillCFreshness: C★ 2Claude Code +9 - 0.433score
generic-docs
Brothelmdzz
通用文档更新 — 扫描代码变更自动更新 README 和 API 文档。
SkillDFreshness: D★ 2Claude Code +9 - 0.433score
generic-product-prd
Brothelmdzz
产品需求文档 — 面向产品经理的多轮需求对齐，产出含用户故事、验收标准、优先级矩阵的结构化 PRD。
SkillDFreshness: D★ 2Claude Code +9 - 0.428score
research
Brothelmdzz
代码库研究 — 委托给 generic-research。并行 subagent 扫描，产出结构化研究文档。
SkillDFreshness: D★ 2Claude Code +9 - 0.428score
implement
Brothelmdzz
按 plan 逐 Phase 实现代码变更 — 委托给 generic-implement。
SkillDFreshness: D★ 2Claude Code +9 - 0.270score
dev
Brothelmdzz
No description from the publisher yet.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 29, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Brothelmdzz/dev-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Brothelmdzz
- 0.501score
generic-test
Brothelmdzz
通用测试执行 — 自动检测项目测试框架，运行测试，验证功能正确性。支持 pytest/jest/gradle/cargo 等。
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
generic-tdd
Brothelmdzz
TDD 模式实现 — RED-GREEN-REFACTOR 循环，先写测试再写代码。与 implement 阶段集成，强制测试优先。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-frontend-research
Brothelmdzz
通用前端代码库研究 — 并行 subagent 扫描前端代码结构，产出结构化研究报告。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-research
Brothelmdzz
通用代码库研究 — 并行 subagent 扫描代码库，产出结构化研究报告。适用于任何项目。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-implement
Brothelmdzz
通用计划执行 — 按 plan 文档逐 Phase 实现代码变更，自动门禁验证。
SkillCFreshness: C★ 2Claude Code +9 - 0.498score
generic-frontend-implement
Brothelmdzz
通用前端实现 — 检测前端技术栈，按 plan 逐 Phase 实现组件/页面/路由变更，自动门禁验证。
SkillCFreshness: C★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get generic-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
generic-audit skill. Agent Mart. https://agentmart.dev/skills/brothelmdzz-generic-audit (last updated 2026-10-24)