xxih/ai-harness-zh/qa
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
系统化 QA 测试并修复发现的问题。先测试,再按 bug 逐个修、逐个重新验证, 并为每个修复补回归测试。 (gstack)
Install
npx vskill@latest install xxih/ai-harness-zh/qaSKILL.md
/qa
/qa 是 gstack 的“测试 -> 修复 -> 再验证”闭环。
模式
Diff-awareFullQuickRegression
核心流程
- setup:浏览器与测试基础设施检查。
- 若仓库没有测试框架,可执行
Test Framework Bootstrap。 - 建立 QA baseline:
- 初始化
- 鉴权
- 定向浏览
- 探索
- 记录
- 收尾
- 计算 health score。
TriageFix Loop
- 定位源码
- 修复
- 提交
- 复测
- 分类
- 补 regression test
Final QAReportTODOS.md Update
关键规则
- 每个 bug 修复都要重新验证。
- 修复应尽量原子化,方便回滚和归因。
qa不只是发现问题,还默认尝试把高价值问题解决掉。
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingreferences/translations/gstack/qa/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/xxih/ai-harness-zh/qa)