Skip to main content
#1
Ranked #1 of 93 in this category· 该品类排名 #1 / 共 93 个

QA Loop

by Anya Raghavan✓ verified author · 已验证·3mo ago

Open the product, try the flow, fix what breaks, repeat.

打开产品走一遍流程,发现问题就修,然后再验证。

Testing & DebuggingCodexBrowser automationMedium risk · 中风险trusted · 官方/可信open source · 开源

Before you install安装前须知

!Accesses the network会访问网络
Editor's verdict· 编辑结论

Best browser QA pick when you need evidence to leave a paper trail. Each run produces screenshots, console diffs, and a reproducible action log — much harder for stakeholders to wave off than "I tested it locally." Works well as a pre-merge gate and for filing bugs with repro steps attached. Not for unit tests, and not for authenticated production sessions where the screenshot itself becomes a data risk.

做需要留证据链的浏览器 QA,它是最佳选择。每次跑都会产出截图、控制台 diff 和可重放的动作日志——比一句「我在本地测过了」更难被挡回去。适合做合并前关卡,也适合带证据提 bug。别用在单元测试场景,也别在敏感的登录态生产会话里用——截图本身就是数据风险。

— Editorial team · 编辑团队

Install via Skills CLI

Use npx skills add to install this skill into the selected agent. Phase 0 commands are generated from source rules, not verified.

Codex
npx skills add https://github.com/anya-raghavan/qa-loop -g -a codex -y

Drop `-g` to install project-locally

Best for适合什么场景

  • Browser smoke tests浏览器冒烟测试
  • Responsive QA响应式 QA
  • Bug reproduction with screenshots带截图的问题复现

Not for不适合什么场景

  • Pure unit testing纯单元测试
  • Sensitive authenticated production sessions高度敏感的登录态生产环境
  • Tasks without a runnable UI没有可运行 UI 的任务

vs alternativesvs 其他选择

Full compare table完整对比表 →
#3GStack QA

Open the app, test the flow, fix what breaks.

4.8·123k stars
diff · 差异Best when browser QA needs to close the loop — find the bug, propose the fix, verify the fix, leave evidence. Where qa-loop emphasizes evidence trails for stakeholder reporting, gstack-qa emphasizes shipping the fix in the same session. Strongest on frontend refactors and visual regressions. Same screenshot data-risk caveat as qa-loop: don't point it at authenticated production sessions where the screenshot itself becomes a leak.
Incident Investigate

No fixes until the cause is real.

4.8·10k stars
diff · 差异Best for incidents where the fastest reflex would be the wrong fix. Forces an evidence-before-action loop: collect logs, list candidate hypotheses, verify each, only then propose a change. Pays for itself the moment it catches the kind of incident where "just restart it" would have masked a real data-integrity problem. Skip it for obviously cosmetic regressions — the cost of slowing down outweighs the cost of a re-deploy there.
Review Radar

Find the bugs, regressions, and missing tests first.

4.8·11k stars
diff · 差异Best when you want PR review insights without committing to a full review workflow. Surfaces the same regression-and-missing-tests signal as gstack-review, but in a quieter, suggestion-only mode — no fix application, no diff edits, no comment threads. Strongest for senior engineers who want a second opinion before they merge their own PR. Weakest when the goal is gating others' code; for that, gstack-review's heavier loop pays off.

Side-by-side compare维度对比

Key differences with same-lane alternatives
this skill · 当前QA LoopGStack QAIncident InvestigateReview Radar
Rating · 评分4.94.84.84.8
Stars · 星标15k123k10k11k
Risk · 风险Medium risk · 中风险Medium risk · 中风险Low risk · 低风险Low risk · 低风险
Best for · 最适合Browser smoke testsOpen the app, test the flow, fix what breaks.Root-cause analysisFind the bugs, regressions, and missing tests first.
Not for · 不适合Pure unit testingWorkflows that require stronger human review than this catalog entry documents.Quick cosmetic fixesWorkflows that require stronger human review than this catalog entry documents.

Audit notes审计备注

last reviewed 2026-06-10 · 复查
Source源码open on GitHub · 公开
Author作者verified org · 已验证
Network网络访问network access · 需联网
Filesystem文件写入writes to repo · 写入仓库!
Dependencies依赖many deps · 依赖较多
Telemetry遥测none · 无
Skill Market
Find the best AI skills for the job·按品类找最好用的 AI 技能
v0.4 · 1306 skills indexed · last review 2026-06-10