catstudy-quality-gate
开发完成后的自检门禁:愿景对照 + spec 合规 + 测试/lint/build 验证。 Use when: 开发完了准备提 review、声称完成了、准备交付。 Not for: 收到 review 反馈(用 catstudy-receive-review)。 Output: Quality Gate 合规报告。
Skill by JianHun101
Chalk Labs
Need help deploying catstudy-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.
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-catstudy-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.
About
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/catstudy-quality-gate
What's inside
- Skill name
catstudy-quality-gate- Description
- 开发完成后的自检门禁:愿景对照 + spec 合规 + 测试/lint/build 验证。 Use when: 开发完了准备提 review、声称完成了、准备交付。 Not for: 收到 review 反馈(用 catstudy-receive-review)。 Output: Quality Gate 合规报告。
- License
- MIT
- Instructions
- 122 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "catstudy-quality-gate" does not match folder "quality-gate"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Quality Gate(质量门)
开发完成到提 review 之间的自检关卡:对照需求自检 + 用真实命令输出证明声明。
## 核心知识
**两条铁律合一**:
1. **与需求对齐**:回读用户原始需求,再逐项验收
2. **承诺需要证据**:没有运行命令、没看到输出,就不能说"通过了"
> 铁律:`NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE`
>
> 自问:"我是这次真的运行了命令并看到输出,还是只是相信它能工作?"
## 流程
```
BEFORE 声称完成 / 提 review:
Step 0: VISION CHECK(愿景核对)
① 回读用户原始需求(对话记录)
② 读核心诉求:"我要..."、"我不想..."
③ 问自己:用户实际使用这个功能时,体验是什么样的?
④ 需求是否完整覆盖了用户的原始意图?
→ 如有遗漏,先确认再继续
Step 1: FIND — 找 spec/plan 文档
- 相关的 feature spec 或实现计划
- 设计讨论和架构决策记录
Step 2: CREATE — 建检查清单
- 列出每一个功能点 / 边界条件
- 列出用户描述的使用场景
Step 3: VERIFY — 逐项检查
- 代码在哪?有测试覆盖?边界处理了吗?
- 前端改动 → 有截图/录屏证据吗?
- markdown/v-html 相关改动 → XSS 防护到位吗?
Step 4: RUN — 运行验证命令(必须这次真实运行)
pnpm test # 必须全部通过
pnpm lint # 0 errors
pnpm build # exit 0
Step 5: READ — 完整读输出,看 exit code,数失败数
Step 6: REPORT — 输出合规报告 + 证据
```
## Quick Reference
| Claim | 需要 | 不够用 |
| --------- | ------------------------ | ----------------------- |
| 测试通过 | 这次运行输出:0 failures | "上次跑过"、"应该通过" |
| lint 干净 | lint 输出:0 errors | 部分检查、推断 |
| 构建成功 | build 命令:exit 0 | lint 通过不代表编译通过 |
| Bug 修了 | 原症状复现测试 | 代码改了,以为修了 |
| 需求满足 | 逐项打勾 | 测试通过就完事 |
**合规报告模板**:
```markdown
## Quality Gate Report
原始需求: {用户原话}
检查时间: YYYY-MM-DD HH:MM
### 愿景覆盖(Step 0)
| # | 用户原始需求 | 覆盖? | 实现? |
| --- | ------------ | ------ | ------ |
| 1 | "我要 XXX" | AC#3 | ✅ |
### 功能验收
| # | 要求 | 状态 | 代码位置 | 测试覆盖 |
| --- | ---- | ---- | ----------- | ------------ |
| 1 | XXX | ✅ | file.ts:L10 | test.spec.ts |
### 验证命令输出(必须是这次真实运行)
pnpm test → {N}/{N} pass ✅
pnpm lint → 0 errors ✅
pnpm build → exit 0 ✅
### Open Questions
- {如果有未解决的问题,在这里列出}
- {全部解决才能提 review}
```
## Common Mistakes
| 错误 | 正确做法 |
| ------------------------- | --------------------------------- |
| 只检查 AC,没回读原始需求 | Step 0 先读用户原始需求 |
| "上次跑测试是通过的" | 这次重新跑,看输出,再声明 |
| "应该没问题" | Run the command. Read the output. |
| 测试通过就声称完成 | 还要对照需求逐项检查 |
| 前端功能没有截图证据 | 附上截图/录屏 + 映射表 |
**Red flags — 立刻 STOP**:
- 用 "should"、"probably"、"seems to"
- 表达满足感("好了!"、"完成!")时还没运行命令
- 信任 subagent 的 "success" 报告而没独立验证
## 和其他 skill 的区别
| Skill | 关注点 | 时机 |
| ---------------------------- | -------------------- | ---------------- |
| **quality-gate(本 skill)** | 对照需求 + 证据验证 | 提 review 之前 |
| `catstudy-receive-review` | 处理 reviewer 的反馈 | 收到 review 之后 |
一句话:quality-gate 是"你自己检查自己",receive-review 是"你处理审查者的意见"。
## 下一步From JianHun101/catStudio, MIT.
More from JianHun101/catStudio
- 0.524score
break-tunnel-vision
JianHun101
跳出牛角尖方法论。Use when 同一个方向反复修复失败(2+ 次)、每次修完还是同样的错、钻在某个自认为的原因里出不来、用户说"你的思路错了/想想别的方向"。 Not for 第一次修复就成功的常见 bug(用 diagnosing-bugs)。 Output 重新锚定——停止 + 新方向 +…
SkillBFreshness: BClaude Code +9 - 0.524score
on-site-project
JianHun101
驻场外部项目工作方法论。Use when 被派到外部/第三方项目做改动(非本仓库)、接手陌生技术栈、需跨长会话持续可信排障、改动会覆盖用户真实数据。 Not for 本仓库内的常规开发(用 implement)、纯讨论、已知原因的简单修复。 Output 清晰的项目认知 + 持续可信的过程文档 + 可回退的改动。
SkillBFreshness: BClaude Code +9 - 0.524score
prototype
JianHun101
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations…
SkillBFreshness: BClaude Code +9 - 0.524score
quality-gate
JianHun101
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.
SkillBFreshness: BClaude Code +9 - 0.524score
receive-review
JianHun101
接收并处理审查反馈。逐项核实审查发现,按严重度分类处理,拒绝表演性同意。Use when another agent's review feedback arrives after a code review.
SkillBFreshness: BClaude Code +9 - 0.524score
request-review
JianHun101
发起审查请求前的前置门槛与轮次规则。六条 BLOCKED 门槛不满足则请求发不出去;同型 finding 二犯触发 failure-mode audit;同对象 ≥3 轮停手升级到需求/方案层。Use when a code change has passed self-check and you are…
SkillBFreshness: BClaude Code +9 - 0.520score
catstudy-receive-review
JianHun101
处理审查者反馈:Red→Green 修复 + 技术论证(禁止表演性同意)。 Use when: 收到 review 结果、审查者提了 P1/P2、需要处理反馈。 Not for: 发 review 请求(用 catstudy-request-review)、自检(用 catstudy-quality-gate)。…
SkillBFreshness: BClaude Code +9 - 0.504score
git-guardrails-claude-code
JianHun101
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillBFreshness: BClaude Code +9 - 0.504score
diagnosing-bugs
JianHun101
Diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.499score
improve-codebase-architecture
JianHun101
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9 - 0.499score
codebase-design
JianHun101
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
JianHun101
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9
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
- Repository
- github.com/JianHun101/catStudio
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from JianHun101
- 0.524score
prototype
JianHun101
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations…
SkillBFreshness: BClaude Code +9 - 0.524score
receive-review
JianHun101
接收并处理审查反馈。逐项核实审查发现,按严重度分类处理,拒绝表演性同意。Use when another agent's review feedback arrives after a code review.
SkillBFreshness: BClaude Code +9 - 0.524score
break-tunnel-vision
JianHun101
跳出牛角尖方法论。Use when 同一个方向反复修复失败(2+ 次)、每次修完还是同样的错、钻在某个自认为的原因里出不来、用户说"你的思路错了/想想别的方向"。 Not for 第一次修复就成功的常见 bug(用 diagnosing-bugs)。 Output 重新锚定——停止 + 新方向 +…
SkillBFreshness: BClaude Code +9 - 0.524score
on-site-project
JianHun101
驻场外部项目工作方法论。Use when 被派到外部/第三方项目做改动(非本仓库)、接手陌生技术栈、需跨长会话持续可信排障、改动会覆盖用户真实数据。 Not for 本仓库内的常规开发(用 implement)、纯讨论、已知原因的简单修复。 Output 清晰的项目认知 + 持续可信的过程文档 + 可回退的改动。
SkillBFreshness: BClaude Code +9 - 0.524score
quality-gate
JianHun101
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.
SkillBFreshness: BClaude Code +9 - 0.524score
request-review
JianHun101
发起审查请求前的前置门槛与轮次规则。六条 BLOCKED 门槛不满足则请求发不出去;同型 finding 二犯触发 failure-mode audit;同对象 ≥3 轮停手升级到需求/方案层。Use when a code change has passed self-check and you are…
SkillBFreshness: BClaude 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 catstudy-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.
Cite this page
catstudy-quality-gate skill. Agent Mart. https://agentmart.dev/skills/jianhun101-catstudy-quality-gate (last updated 2026-10-24)