Token导航 LogoToken导航

Agent Skill · 研究检索

qc-specialist(质检专家)

qc-specialist 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

qc-specialist 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 45,786。

总安装 824周安装 33GitHub Stars 6下载 267核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:qc-specialist(质检专家)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/qc-specialist
安装命令:
npx skills add https://github.com/duc01226/easyplatform --skill qc-specialist
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/duc01226/easyplatform --skill qc-specialist

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

qc-specialist 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

适用于需要从 GitHub 或其他来源提取结构化信息的场景。

来源仓库内路径:skills/qc-specialist

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/duc01226/easyplatform --skill qc-specialist;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

qc-specialist 怎么安装?

在终端执行 npx skills add https://github.com/duc01226/easyplatform --skill qc-specialist。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

qc-specialist 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

qc-specialist 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

qc-specialist 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

qc-specialist 用的人多吗?

公开数据是累计安装 824 次,近一周安装 33 次,下载 267 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

qc-specialist 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
qc-specialist

质检专家 · 本页

8246需要联网MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
  • docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected:...] header before reading)

Quick Summary

Goal: Enforce quality gates, verify compliance with standards, and track quality metrics across the development lifecycle.

Workflow:

  1. Identify Gate — Determine which quality gate applies (Idea>PBI, PBI>Dev, Dev>QA, QA>Release)
  2. Verify Checklist — Run through pass/fail criteria for the gate stage
  3. Generate Report — Produce PASS/FAIL/CONDITIONAL gate status with evidence
  4. Track Metrics — Log in audit trail and update quality metrics dashboard

Key Rules:

  • Every gate must have a clear PASS/FAIL/CONDITIONAL status
  • Evidence must be provided for critical checklist items
  • Sign-offs are required before release gates can pass

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

QC Specialist Assistant

Help QC Specialists enforce quality gates, verify compliance with standards, and track quality metrics across the development lifecycle.


Core Capabilities

1. Quality Gates

Define pass/fail criteria at each stage:

Gate: Idea → PBI
  • Problem statement present
  • Business value articulated
  • No technical solution prescribed
  • Target users identified
Gate: PBI → Development
  • Acceptance criteria in GIVEN/WHEN/THEN
  • Out of scope defined
  • Dependencies identified
  • Design approved (if applicable)
Gate: Development → QA
  • Code review approved
  • Unit tests >80% coverage
  • No P1/P2 linting errors
  • Documentation updated
Gate: QA → Release
  • All test cases executed
  • No open P1/P2 bugs
  • Regression suite passed
  • PO sign-off received

2. Compliance Verification

  • Code follows architecture patterns
  • Security requirements met
  • Accessibility standards (WCAG 2.1 AA)
  • Performance benchmarks

3. Audit Trail

Track artifact lifecycle:

{Artifact} | {Action} | {By} | {Date} | {Notes}

4. Quality Metrics

Code Quality
  • Cyclomatic complexity
  • Code coverage %
  • Technical debt ratio
  • Duplication %
Process Quality
  • Defect escape rate
  • First-time-right %
  • Cycle time
  • Lead time

Quality Gate Checklists

Pre-Development Checklist

## Quality Gate: PBI Ready for Development

**PBI:** {PBI-ID}
**Reviewer:** {Name}
**Date:** {Date}

### Requirements

- [ ] Clear problem statement
- [ ] User value articulated
- [ ] Acceptance criteria in GIVEN/WHEN/THEN format
- [ ] Out of scope explicitly listed

### Design

- [ ] Design spec approved (if UI changes)
- [ ] API contract defined (if backend changes)
- [ ] Database changes documented (if applicable)

### Dependencies

- [ ] Upstream dependencies identified
- [ ] No blocking dependencies
- [ ] Integration points documented

### Gate Status: PASS / FAIL / CONDITIONAL

**Notes:**
{Any concerns or conditions}

Pre-Release Checklist

## Quality Gate: Ready for Release

**Feature:** {Feature name}
**Release:** {Version}
**Date:** {Date}

### Testing

- [ ] All test cases executed
- [ ] Pass rate: \_\_\_\_%
- [ ] No open P1 bugs
- [ ] No open P2 bugs (or exceptions approved)

### Code Quality

- [ ] Code review approved
- [ ] Coverage > 80%
- [ ] No security vulnerabilities
- [ ] Performance benchmarks met

### Documentation

- [ ] User documentation updated
- [ ] API documentation current
- [ ] Release notes drafted

### Sign-Offs

- [ ] QA Lead: **\*\***\_**\*\*** Date: **\_\_\_**
- [ ] Dev Lead: **\*\***\_**\*\*** Date: **\_\_\_**
- [ ] PO: **\*\*\*\***\_\_**\*\*\*\*** Date: **\_\_\_**

### Gate Status: PASS / FAIL

**Release Decision:**
{Go / No-Go with notes}

Workflow Integration

Running Quality Gate

When user runs /quality-gate {artifact-or-pr}:

  1. Identify gate type based on artifact/stage
  2. Load appropriate checklist
  3. Verify each criterion
  4. Generate pass/fail report
  5. Log in audit trail

Metrics Dashboard Template

## Quality Metrics - Sprint {N}

### Code Quality

| Metric      | Target | Actual | Trend |
| ----------- | ------ | ------ | ----- |
| Coverage    | >80%   |        | ↑↓→   |
| Complexity  | <15    |        |       |
| Duplication | <5%    |        |       |
| Debt Ratio  | <10%   |        |       |

### Process Quality

| Metric            | Target | Actual |
| ----------------- | ------ | ------ |
| Defect Escape     | <5%    |        |
| First-Time-Right  | >90%   |        |
| Avg Review Cycles | <2     |        |

### Defect Trends

| Sprint | Found | Fixed | Escaped |
| ------ | ----- | ----- | ------- |
| N-2    |       |       |         |
| N-1    |       |       |         |
| N      |       |       |         |

Output Conventions

File Naming

{YYMMDD}-qc-gate-{stage}-{slug}.md
{YYMMDD}-qc-audit-{feature}.md
{YYMMDD}-qc-metrics-sprint-{n}.md

Quality Checklist

Before completing QC artifacts:

  • All checklist items verified
  • Evidence provided for critical items
  • Sign-offs captured
  • Gate status clearly stated
  • Audit trail updated

Related

  • test-spec
  • code-review

Closing Reminders

  • IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
  • IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
  • IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
  • IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

平台分布

Claude Code

29.66%
按下载量换算79

windsurf

22.76%
按下载量换算61

OpenCode

16.81%
按下载量换算45

Codex

12.11%
按下载量换算32

Antigravity

8.55%
按下载量换算23

Gemini CLI

3.9%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills