Menu
用于功能验收、回归验证、确认修复是否生效，以及需要用真实界面、视频或日志证据判断用户流程是否正常的任务。适用于“验收一下”“测一下”“确认修复”“给我可复核证据”等请求。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | feature-acceptance |
| description | 用于功能验收、回归验证、确认修复是否生效，以及需要用真实界面、视频或日志证据判断用户流程是否正常的任务。适用于“验收一下”“测一下”“确认修复”“给我可复核证据”等请求。 |
把验收请求转成可复现、可复核的结论。优先验证用户可观察的行为，不用代码阅读、模拟页面或单个 API 响应替代真实流程。
每个用例和整体结论只能是 PASS / FAIL / BLOCKED / NOT RUN。
PASS：预期结果与关键断言满足，证据已经复核。FAIL：结果、错误提示、数据变化或技术断言不符合预期。BLOCKED：缺少明确的环境、权限、账号、数据或外部依赖。NOT RUN：本轮未执行的非核心用例，必须说明未覆盖风险。不要用“看起来正常”替代结论。用户明确要求的核心用例不能无理由标为 NOT RUN。
skills/e2e-testing/SKILL.md，必要时委派 agents/e2e-runner.md。skills/systematic-debugging/SKILL.md，不要在验收报告中猜测修复方案。skills/verification-before-completion/SKILL.md 的新鲜验证证据要求。记录被测功能、真实用户入口、核心成功标准、环境前置条件和不可执行的高风险动作。没有测试前置条件时先标记 BLOCKED，不要通过注入凭据、篡改本地状态或破坏共享数据绕过。
先写用例矩阵，再开始操作：
| ID | 场景 | 前置条件 | 步骤 | 期望结果 | keyNodes | evidenceMedium | 结果 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| A1 | 主成功路径 | 已启动服务 | 从真实入口完成操作 | 用户可见结果正确 | 入口 / 操作 / 结果 | image | NOT RUN |
keyNodes 写明名称、重要性、预期观察和证据角色。evidenceMedium 只能是 image、video 或 log。关键节点超过 10 个或需要表达过程时用 video。image 或 video 必须来自真实产品页面或应用界面；API、数据库或脚本输出只作为辅助 log 证据。在目标项目工作区的已忽略临时目录保存需要持久复核的产物，例如 tmp/acceptance/<run-id>/。每个用例单独保存截图、视频或日志，并记录来源 URL/窗口、采集时间、采集前动作和对应的 keyNodes。
failureReason 与缺失条件。主 agent 必须二次审核每份关键证据，不能只引用执行者的自报结论。
image：确认可渲染、来源真实、URL 和关键节点正确，且不是空白页、登录页或无关页面。video：确认时长合理，并覆盖触发、过程和完成信号。log：确认关键断言存在，且没有与结论冲突的相关错误。任何 image/video 用例未完成二次审核时，整体不能是 PASS。
报告保持简短但可复核：
结论：PASS / FAIL / BLOCKED / NOT RUN
被测功能：
被测地址 / 命令：
用例结果：
| ID | 场景 | 结果 | 原因 | 关键证据 |
二次审核：已打开的证据；改判原因
技术摘要：相关 console / 网络 / 服务端错误
未覆盖风险：
核心用例任一 FAIL 时整体为 FAIL；没有 FAIL 但核心用例 BLOCKED 时整体为 BLOCKED；核心用例全部 PASS 且证据审核完成时整体才为 PASS。
Stress-test a plan, design, decision, or idea through a one-question-at-a-time interview. Use when the user invokes /grill, says grill me, asks to be challenged, 拷问, 压力测试, or wants a plan stress-tested; also use when progress is blocked by an unresolved user-owned decision whose alternatives materially change the outcome after high-risk classification is ruled out. Do not use merely because work is complex, high-risk, new, or spans multiple files.
Use when the user explicitly requests Brainstorming, a design spec, Spec Gate, or the full Superpowers workflow; also use automatically for costly-to-reverse high-risk work involving architecture or service boundaries, public-contract compatibility, authentication or authorization, persistent data/schema migration, or irreversible external side effects. Do not use for ordinary behavior changes or merely because work is new, complex, or spans multiple files.
Chinese workflow for surfacing systematic fact, evidence, context, and blind-spot gaps before, during, and after agentic work. Use when the user explicitly asks for a blind-spot scan, unknown unknowns, prototypes, reference mapping, implementation notes, explainers, or quizzes; when phrases like "I'll know it when I see it" or "teach me this domain" expose unstated assumptions; or when safe progress is blocked by evidence gaps that require multiple low-cost probes. Do not use merely because work is complex, high-risk, long-running, or spans multiple files.
Use when starting or routing a non-trivial task in this workflow harness, when the user references Superpowers, or when deciding which skill, command, rule, or agent should govern the work. Establishes skill invocation discipline: check relevant process skills before acting, follow user/project instructions first, and verify before completion.
Use when you have a spec or requirements for a multi-step task, before touching code
为 subagent、代码探索、RAG 式检索和大仓库上下文收集设计迭代检索闭环。用于初始上下文不明确、一次性读全仓会污染上下文、子代理不知道该读哪些文件、或搜索结果需要逐轮收敛时。