$ loading_
在宣称任务完成或修复成功前，先执行验证并用结果佐证结论。
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "verification-before-completion" 技能： 1. 下载 https://raw.githubusercontent.com/obra/superpowers/main/skills/verification-before-completion/SKILL.md 2. 保存为 ~/.claude/skills/verification-before-completion/SKILL.md 3. 装好后重载技能，告诉我可以用了
我刚修复了登录接口的报错。请先不要直接说“已修复”，而是列出应执行的验证命令、说明每一步要检查的输出，并在我贴出结果后再判断是否真的修复完成。
先给出测试或验证步骤、通过标准与所需证据，再根据实际输出判断是否可宣称修复成功。
在创建 PR 之前，帮我检查这个项目应运行哪些构建、测试和静态检查命令。只有当这些命令输出符合预期时，才能得出“可以提交 PR”的结论。
输出一套 PR 前验证清单，并强调必须依据命令结果而不是主观判断来下结论。
我认为数据清洗脚本已经跑通。请先设计验证方案，包括运行命令、关键日志、样本结果和异常检查项；在没有看到这些证据前，不要说任务已完成。
给出面向数据流程的验证步骤和验收标准，确保先看证据再确认任务完成。
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors |
| Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
Requirements:
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
Agent delegation:
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
From 24 failure memories:
ALWAYS before:
Rule applies to:
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
在开发分支完成并通过测试后，帮助选择合并、提 PR 或清理收尾方案。
为 Claude Code 会话提供系统化校验流程，帮助检查结果正确性与质量。