Skip to content
Agentmart
Submit a tool

quality-gate

代码变更提交审查前的自查门。检查编码规范、测试覆盖、架构边界、安全性和未完成项。通过后由作者按 request-review 自行发起审查请求。Use when a code change is finished and needs a self-check before review.

Skill by JianHun101

IndexedMIT
Write a review

Chalk Labs

Need help deploying quality-gate?

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.

Book a call

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/jianhun101-quality-gate

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.

We use your email only for this newsletter. Privacy

About

代码变更提交审查前的自查门。检查编码规范、测试覆盖、架构边界、安全性和未完成项。通过后由作者按 request-review 自行发起审查请求。Use when a code change is finished and needs a self-check before review. Not for pure conversation without code changes, exploration, or when already inside the review loop. Output a Quality Gate Report (PASS/FAIL with per-item results).

Use cases: documents

No 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/quality-gate

What's inside

Skill name
quality-gate
Description
代码变更提交审查前的自查门。检查编码规范、测试覆盖、架构边界、安全性和未完成项。通过后由作者按 request-review 自行发起审查请求。Use when a code change is finished and needs a self-check before review. Not for pure conversation without code changes, exploration, or when already inside the review loop. Output a Quality Gate Report (PASS/FAIL with per-item results).
License
MIT
Instructions
159 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# quality-gate

提交审查前的自查门。作者在发给其他猫审查之前,先自己检查一遍。

## 何时使用

- 完成一个代码变更后
- 发起审查请求(`request-review`,由作者自行发起)之前(前置条件)
- 对已有代码做改动后自查

## 不使用的情况

- 纯对话/回答用户问题(无代码变更)
- 探索/调研阶段
- 已经在审查循环中(receive-review 处理后)

## 检查步骤

### 步骤 1:VISION CHECK(需求对齐)

回到原始需求和讨论,确认:

- [ ] 改动实现了用户/任务要求的所有功能
- [ ] 没有范围蔓延(多做了不相关的改动)
- [ ] 如果有 .pen 设计文件,与实现做视觉对比

### 步骤 2:CODING STANDARDS CHECK(编码规范)

对照 `CODING_STANDARDS.md`(项目根目录)逐项检查:

- [ ] 包结构:代码放在正确的 monorepo 包中
- [ ] TypeScript:无 `any`,Zod 校验覆盖 API 边界,命名转换正确
- [ ] 测试:测试通过,覆盖新增/修改的功能
- [ ] 命名:文件 kebab-case,组件 PascalCase,函数 camelCase
- [ ] 错误处理:非阻塞降级、超时保护、结构化日志
- [ ] Vue:scoped 样式、v-html 经 DOMPurify
- [ ] 数据库:幂等迁移、JSON 字段处理、WAL 模式

### 步骤 3:TEST EVIDENCE(测试证据)

```bash
pnpm test
pnpm lint
```

确认:

- [ ] 所有测试通过
- [ ] 无新增 lint 错误
- [ ] 测试覆盖了新功能的关键路径

### 步骤 4:ARCHITECTURE BOUNDARY(架构边界)

- [ ] 依赖方向正确(shared ← server ← web)
- [ ] 无跨包直接引用(server 不 import web 代码)
- [ ] 新文件位置合理
- [ ] 如有新依赖,已声明并获批准

### 步骤 5:SECURITY SWEEP(安全扫描)

- [ ] 无硬编码的密钥/Token/密码
- [ ] `v-html` 已通过 DOMPurify 消毒
- [ ] API 输入有 Zod 校验
- [ ] 无 `eval()`、`new Function()`、`innerHTML` 裸赋值
- [ ] SQL 查询使用参数化(无字符串拼接)

### 步骤 6:UNFINISHED BUSINESS(未完成项扫描)

- [ ] 无 TODO/FIXME/HACK 注释(或已明确标记为有意保留)
- [ ] 无被注释掉的代码块
- [ ] 无 `console.log` 调试语句
- [ ] 无 `only`/`skip` 标记的测试(`test.only`、`it.skip`)

### 步骤 7:SELF-DOGFOOD(自测)

如果是用户可见的功能变更:

- [ ] 启动应用(`pnpm dev`)验证功能正常工作
- [ ] 至少走通一条完整的用户路径

### 步骤 8:TWO-AXIS SELF-CHECK(双轴自查,code-review 方法论)

code-review 把审查拆成两条独立轴,自查同样过两轴——**一条轴过了不代表另一条**:

- **Standards 轴**:代码是否符合项目文档化编码规范(CODING_STANDARDS.md)?
- **Spec 轴**:代码是否忠实实现发起它的 spec/issue/需求(无缺失、无范围蔓延)?

两轴分开核对,别在「代码很干净」的满足感里跳过 Spec 轴的逐条需求对齐;也别在「需求都对上了」里跳过规范检查。

### 步骤 9:SMELL SWEEP(坏味道扫描,Fowler 基线)

对照 code-review 的 smell baseline 扫自己的 diff(文档化规范优先于基线;每条是判断标签不是硬违规;工具已强制的跳过):

- Mysterious Name / Duplicated Code / Feature Envy / Data Clumps / Primitive Obsession
- Repeated Switches / Shotgun Surgery / Divergent Change / Speculative Generality
- Message Chains / Middle Man / Refused Bequest

命中 → Gate 报告列出,能当场修就修;不能修 → 作为 Open Question 点名具体文件/符号给审查者。

## 输出

自查通过后,输出以下格式:

```
## Quality Gate Report

### Vision Check
✅ 所有需求已实现 / ⚠️ 以下需求未覆盖:...

### Standards Check
✅ 通过 / ❌ 以下项目未通过:...

### Test Evidence
pnpm test → N passed, 0 failed
pnpm lint → 通过 / M errors

### Architecture
✅ 边界正确 / ❌ 以下问题:...

From JianHun101/catStudio, MIT.

More from JianHun101/catStudio

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from JianHun101

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 quality-gate 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying quality-gate?

CallGet help
Cite this page

quality-gate skill. Agent Mart. https://agentmart.dev/skills/jianhun101-quality-gate (last updated 2026-10-24)