メニュー
Use before claiming work is complete, fixed, passing, ready for PR, or moving to the next task. Requires fresh verification evidence from this turn, with exact commands, results, skipped checks, and remaining risk.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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
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。
| name | verification-before-completion |
| description | Use before claiming work is complete, fixed, passing, ready for PR, or moving to the next task. Requires fresh verification evidence from this turn, with exact commands, results, skipped checks, and remaining risk. |
Use this skill before any success or completion claim.
Core rule: do not say work is complete, fixed, passing, or ready unless fresh verification evidence from this turn supports that claim.
Before making a completion claim:
If verification cannot run, say that it was not run and explain the remaining risk. Do not replace evidence with confidence.
| Claim | Required evidence |
|---|---|
| Tests pass | Fresh test command output with exit code 0 or an exact pass count |
| Build succeeds | Fresh build command output with exit code 0 |
| Lint is clean | Fresh lint command output with zero reported errors |
| Bug is fixed | Fresh reproduction or regression test showing the original symptom no longer occurs |
| Task is complete | Spec, plan, or user request checklist verified against the changed files |
Ready for /pr | /verify or equivalent checks with skipped checks and risks stated |
| Agent work is done | Independent inspection of the diff and required verification, not only the agent report |
Stop and verify before using language like:
If verification fails:
skills/systematic-debugging/SKILL.md before changing code.If verification is partial:
Use this compact format in final summaries and task checkpoints:
验证：
- <command>: <passed/failed/not run> — <evidence>
未运行：
- <check>: <reason>
剩余风险：
- <risk or "无已知剩余风险">