菜单
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | verification-before-completion |
| description | Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always |
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
Before running verification, map the claim to evidence:
If no command can prove the claim, use inspection, reproduction steps, or a line-by-line checklist. State the evidence type.
If verification cannot run:
| 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
When a delegated agent reports completion, independently inspect the changed files, confirm the requested behavior is present, and run or perform the verification that proves the delegated claim.
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.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when executing implementation plans with independent tasks in the current session
Use when you have a spec or requirements for a multi-step task, before touching code
Fast, MVP-focused grilling session for plans, prototypes, designs, or feature ideas. Use when the user wants to stress-test direction, clarify assumptions, reduce scope, or get challenged without a long decision-tree interview.
Execute and orchestrate multiple AI agent CLIs (agy, Codex, Cursor, Claude Code, Pi) for getting alternative opinions, comparing approaches, or leveraging different AI models' strengths. Use when the user explicitly mentions agent names like "ask agy", "ask cursor", "ask codex", "ask pi", "use composer", "use pi", "try grok", or when needing diverse perspectives on complex problems, alternative implementation approaches, or multi-agent collaboration.
Summarize a video (URL or local path) by pulling captions first, falling back to audio-only transcription, and optionally extracting frames for visual summaries. Use when the user pastes a YouTube/Vimeo/X/etc URL, points at a local video file, or asks to summarize, watch, or extract takeaways from a video. Triggers on "summarize this video", "what's in this video", "watch this", URLs ending in /watch, /shorts, common video extensions (.mp4/.mov/.mkv/.webm).