メニュー
Use when about to claim work is complete, fixed, passing, ready to commit, or ready for PR, especially after code, docs, config, or validator changes.
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
Use when a request needs product/design exploration, unclear requirements, multiple viable approaches, UI/UX choices, or new behavior whose intent is not yet bounded.
Use when 2+ independent tasks, failures, research lanes, exploration lanes, or path-scoped investigations can run without shared state, shared files, or sequential dependency.
Use when executing a written implementation plan inline in the current session with checkpoints and verification.
Use when adding or changing a capability surface such as a public function, API, command, prompt, workflow, schema/helper, policy, or reusable instruction.
Use when implementation is complete, verification passes, and the remaining decision is how to integrate, merge, PR, clean up, or finish the branch.
Use when creating or revising docs, plans, records, PR text, handoffs, or other prose that should be sparse, direct, and low-context.
| name | verification-before-completion |
| description | Use when about to claim work is complete, fixed, passing, ready to commit, or ready for PR, especially after code, docs, config, or validator changes. |
Purpose: Run the actual verification command, read full output, confirm the claim is supported by evidence before declaring completion. Consumer: Main agent about to claim work complete, fixed, passing, or ready for merge/PR. Failure consequence: False completion claims ship; downstream agents and humans trust stale docs or unverified fixes. Falsifier: Trivial one-liner, single command with no repo consequence, or pure cosmetic change.
Redteam forwarder: For high-stakes claims or contested edge cases, run /redteam:verify (cross-model adversarial verification) before declaring done. Single-model LLM-as-judge is weaker than a redteam panel when the claim is contested.
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.