MCPInstall

qa

交互式 QA 会话,用户以对话方式报告缺陷或问题,代理创建 GitHub issues。后台探索代码库以获取上下文和领域语言。适用于用户想报告缺陷、执行 QA、以对话方式提交 issues,或提到 “QA session” 时。

Installs
2.1K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/vinvcn/mattpocock-skills-zh-cn --skill qa
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads qa automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

QA Session

运行交互式 QA session。用户描述遇到的问题。你负责澄清、探索 codebase 获取 context,并创建 durable、user-focused 且使用项目 domain language 的 GitHub issues。

For each issue the user raises

1. Listen and lightly clarify

让用户用自己的话描述问题。最多问 2-3 个简短 clarifying questions,聚焦:

  • 他们期望什么,实际发生了什么
  • Steps to reproduce(如果不明显)
  • 是否稳定复现,还是 intermittent

不要过度访谈。如果描述足够清楚,可以直接 file。

2. Explore the codebase in the background

与用户对话时,在后台启动 Agent(subagent_type=Explore)理解相关区域。目标不是找 fix,而是:

  • 学习该区域使用的 domain language(检查 UBIQUITOUS_LANGUAGE.md)
  • 理解 feature 本应做什么
  • 识别 user-facing behavior boundary

这些 context 帮助你写出更好的 issue,但 issue 本身不应引用具体 files、line numbers 或 internal implementation details。

3. Assess scope: single issue or breakdown?

file 前判断这是单个 issue,还是需要拆成多个 issues。

拆分条件:

  • fix 跨多个 independent areas(例如 “form validation is wrong AND success message is missing AND redirect is broken”)
  • 存在清晰可分离 concerns,不同人可以并行处理
  • 用户描述了多个不同 failure modes 或 symptoms

保持单个 issue 的条件:

  • 一个地方的一个 behavior 错了
  • symptoms 都来自同一个 root behavior

4. File the GitHub issue(s)

使用 gh issue create 创建 issues。不要先要求用户 review;直接 file 并分享 URLs。

Issues 必须 durable,即 major refactors 后仍有意义。从用户视角写。

For a single issue

使用这个模板:

## What happened

[用普通语言描述用户经历的实际行为]

## What I expected

[描述期望行为]

## Steps to reproduce

1. [developer 可执行的具体编号步骤]
2. [使用 codebase 的 domain terms,不用 internal module names]
3. [包含相关 inputs、flags 或 configuration]

## Additional context

[来自用户或 codebase exploration 的额外观察,用来帮助 framing — 例如 “this only happens when using the Docker layer, not the filesystem layer” — 使用 domain language,但不引用 files]

For a breakdown (multiple issues)

按 dependency order 创建 issues(blockers first),这样可以引用真实 issue numbers。

每个 sub-issue 使用这个模板:

## Parent issue

#<parent-issue-number>(如果你创建了 tracking issue)或 "Reported during QA session"

## What's wrong

[描述这个 specific behavior problem — 只描述这个 slice,而非整个 report]

## What I expected

[这个 slice 的 expected behavior]

## Steps to reproduce

1. [只针对这个 issue 的步骤]

## Blocked by

- #<issue-number>(如果必须等另一个 issue 解决)

如果没有 blockers,写 "None — can start immediately"。

## Additional context

[与这个 slice 相关的额外观察]

创建 breakdown 时:

  • Prefer many thin issues over few thick ones — 每个都应能独立 fix 和 verify
  • Mark blocking relationships honestly — 如果 B 确实必须等 A 才能测试,就说明。如果独立,两个都写 “None — can start immediately”
  • Create issues in dependency order,这样可以在 “Blocked by” 中引用真实 issue numbers
  • Maximize parallelism — 目标是让多人(或 agents)能同时领取不同 issues

Rules for all issue bodies

  • No file paths or line numbers — 它们会过时
  • Use the project's domain language(如果存在,检查 UBIQUITOUS_LANGUAGE.md)
  • Describe behaviors, not code — 写 “the sync service fails to apply the patch”,不要写 “applyPatch() throws on line 42”
  • Reproduction steps are mandatory — 如果无法确定,询问用户
  • Keep it concise — developer 应能 30 秒内读完 issue

file 后,打印所有 issue URLs(并总结 blocking relationships),然后问:“Next issue, or are we done?”

5. Continue the session

持续进行,直到用户说结束。每个 issue 都独立处理,不要 batch。

FAQ

What does the qa skill do?

交互式 QA 会话,用户以对话方式报告缺陷或问题,代理创建 GitHub issues。后台探索代码库以获取上下文和领域语言。适用于用户想报告缺陷、执行 QA、以对话方式提交 issues,或提到 “QA session” 时。

How do I install qa?

Run npx skills add https://github.com/vinvcn/mattpocock-skills-zh-cn --skill qa in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/qa/ (personal) or .claude/skills/qa/ (project).

Which AI agents can use qa?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is qa safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains qa?

It is published by vinvcn in vinvcn/mattpocock-skills-zh-cn. It has 2,142 recorded installs.

More from vinvcn/mattpocock-skills-zh-cn

View all →

grill-me

vinvcn/mattpocock-skills-zh-cn

一个用来打磨计划或设计的持续追问式访谈。

6.7K installs

grill-with-docs

vinvcn/mattpocock-skills-zh-cn

一个用来打磨计划或设计的持续追问式访谈,并在过程中创建文档(ADRs 和词汇表)。

Docs & Writing6.3K installs

setup-matt-pocock-skills

vinvcn/mattpocock-skills-zh-cn

为此仓库配置 engineering skills:设置其 issue tracker、triage labels 词汇与 domain docs 布局。在首次使用其他 engineering skills 前运行一次。

Docs & Writing6K installs

tdd

vinvcn/mattpocock-skills-zh-cn

测试驱动开发。适用于用户想用先写测试的方式构建功能或修复缺陷、提到 “red-green-refactor”,或需要集成测试时。

Testing & QA5.9K installs

handoff

vinvcn/mattpocock-skills-zh-cn

把当前对话压缩成交接文档,让另一个代理接手。

improve-codebase-architecture

vinvcn/mattpocock-skills-zh-cn

扫描代码库中的深化机会,生成可视化 HTML 报告,然后围绕你选中的候选项继续追问。

Popular testing & qa skills

View category →

tdd

mattpocock/skills

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Testing & QA1.2M installs

grilling

mattpocock/skills

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Testing & QA996.2K installs

migrate-to-shoehorn

mattpocock/skills

Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.

Testing & QA484.1K installs

run-train

lllllllama/rigorpilot-skills

Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized trainoutputs/. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.

Testing & QA337.8K installs

test-driven-development

obra/superpowers

Use when implementing any feature or bugfix, before writing implementation code

Testing & QA261.8K installs

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Testing & QA216.8K installs