qa-sweep
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseQA Sweep — multi-lens agent QA of the live product
QA扫描——针对在线产品的多视角Agent QA测试
Read FIRST (the protocol SSOT: environment rules · the five lens briefs ·
findings format · triage) — the lens briefs in agent prompts come verbatim from there, and the
account/mutation policy it sets is a hard rail, not advice. If that file doesn't exist yet,
create it from the layer's protocol template ( in
the kit repo — copy it from there if this project only adopted the layer's files)
and fill the placeholders before sweeping.
projects/<name>/qa/README.md${CLAUDE_PLUGIN_ROOT}/reference/qa-PROTOCOL-TEMPLATE.md.claude/请先阅读（这是协议的唯一可信来源：环境规则·五个视角说明·发现结果格式·问题分级）——Agent提示词中的视角说明完全源自该文件，其中规定的账户/变更策略是硬性要求，而非建议。如果该文件尚未存在，请从层级协议模板（工具包仓库中的——若项目仅采用了层级的文件，请从此处复制模板）创建该文件，并在扫描前填充占位内容。
projects/<name>/qa/README.md${CLAUDE_PLUGIN_ROOT}/reference/qa-PROTOCOL-TEMPLATE.md.claude/Steps
步骤
- Preflight (integrator, by hand): bring up the stack the protocol names (app · API · store) · pick the account per the protocol's policy (the demo/real account = OBSERVE-ONLY always; the seeded sacrificial account = mutation QA only when the run brief grants it) · make sure nothing else is writing to the shared store during the sweep (no integration test suites, no live jobs).
- Pick lenses for this run (default: user-flow + contract in parallel, then edge-state, then honesty + ux-critique). Browser lenses run CONCURRENTLY via the isolated Playwright MCP servers the protocol lists (one server per concurrent browser agent — mechanism + logged-in seed recipe in the protocol § Parallel lenses). Browser lenses: user-flow · edge-state · ux-critique. Non-browser: contract (curl) · honesty (curl + read-only store queries).
- Spawn agents with the lens brief from the protocol § Lens briefs + the run scope (which screens/flows changed recently — QA the delta first, then one broad pass).
qa - Verify before ticketing (the fact-check rule): reproduce every P1/P2 finding yourself (the named repro steps) before it becomes a ticket. Unreproducible → back to the agent or drop with a note. «Impressions» never become tickets directly.
- Land the results: verified findings → backlog tickets (P1/P2) or a minors batch (P3) ·
one run record (lenses run · coverage · findings table with verified/dropped status · pointers to tickets) · a row in the protocol's § Runs index.
projects/<name>/qa/qa-run-YYYYMMDD.md - Cleanup: stop dev servers, remove stray screenshots from the repo root, re-seed the sacrificial account if a mutation run dirtied it.
- **预检（由集成人员手动完成）：**启动协议指定的技术栈（应用·API·存储）·根据协议策略选择账户（演示/真实账户=始终仅用于观测；预填充的专用测试账户=仅在运行说明允许时用于变更类QA测试）·确保扫描期间没有其他进程写入共享存储（无集成测试套件、无在线任务）。
- 选择本次运行的视角（默认：并行执行user-flow + contract，随后执行edge-state，最后执行honesty + ux-critique）。浏览器视角通过协议列出的独立Playwright MCP服务器并发运行（每个并发浏览器Agent对应一台服务器——协议《并行视角》章节中包含机制说明及登录种子配置）。浏览器视角包括：user-flow · edge-state · ux-critique。非浏览器视角：contract（curl）· honesty（curl + 只读存储查询）。
- 生成代理，使用协议《视角说明》章节中的视角描述以及运行范围（最近变更的页面/流程——优先QA变更部分，然后进行一次全面扫描）。
qa - **工单创建前验证（事实核查规则）：**在将每个P1/P2级发现转化为工单前，需自行复现（按照指定的复现步骤）。无法复现的问题→退回Agent处理或标注说明后丢弃。“主观印象”不得直接转化为工单。
- **交付结果：**已验证的发现→转化为待办工单（P1/P2级）或次要问题批次（P3级）·一份运行记录（包含运行的视角·覆盖范围·带验证/丢弃状态的发现结果表格·工单链接）·在协议的《运行记录索引》章节中添加一行记录。
projects/<name>/qa/qa-run-YYYYMMDD.md - **清理工作：**停止开发服务器，移除仓库根目录下的零散截图，若变更类运行导致专用测试账户数据混乱，需重新预填充该账户。