メニュー
Use when about to claim work is complete, fixed, or passing. Requires running verification commands and reading actual output BEFORE making any success claims. Evidence before assertions.
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
Write and organize unit tests for functions, methods, and classes using `package:test`. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.
Uses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.
Define and generate mock objects for external dependencies using `package:mockito` and `build_runner`. Use when unit testing classes that depend on complex external services like APIs or databases.
Execute `dart analyze` to identify warnings and errors, and use `dart fix --apply` to automatically resolve mechanical lint issues. Use during development to ensure code quality and before committing changes.
Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests. Use when adding integration testing to a project, exploring UI components via MCP, or automating user flows with the integration_test package.
Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.
| name | verification-before-completion |
| description | Use when about to claim work is complete, fixed, or passing. Requires running verification commands and reading actual output BEFORE making any success claims. Evidence before assertions. |
Adapted from
superpowers/skills/verification-before-completion. Trimmed.
Evidence before claims, always. Claiming "done" without verification = dishonesty, not efficiency.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you have not run a verification command in this message, you cannot claim it passes.
BEFORE claiming a status or expressing satisfaction:
1. IDENTIFY: which command would prove this claim?
2. RUN: run the full command (fresh, not partial).
3. READ: read the full output, check exit code, count failures.
4. VERIFY: does the output confirm the claim?
- No → state the actual status with the evidence.
- Yes → state the claim WITH the evidence.
5. ONLY THEN: speak the claim.
Skipping any step = lying.
| Claim | Required | Not enough |
|---|---|---|
| "Tests pass" | Test command output: 0 failures | Old run, "should pass" |
| "Linter clean" | Linter output: 0 errors | Partial check, extrapolation |
| "Build OK" | Build command exit 0 | Lint passing, "logs look good" |
| "Bug fixed" | Test that reproduces the bug → passes | Code changed, "assumed fixed" |
| "Regression test works" | Red-green cycle verified (revert fix → fail; restore → pass) | Test passes once |
| "Requirement met" | Line-by-line checklist vs spec | "Tests pass, done" |
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification. |
| "I'm confident" | Confidence ≠ evidence. |
| "Just this once" | No exceptions. |
| "Linter passed" | Linter ≠ compiler ≠ runtime. |
| "I'm tired" | Exhaustion ≠ excuse. |
| "Partial check is enough" | Partial proves nothing. |
✅ "I ran `flutter test test/feed/`. 12/12 pass. Done."
❌ "Tests should pass now."
✅ "I ran `flutter build apk --release`. Exit 0. APK 28MB."
❌ "Lint passed, build is probably OK."
✅ Write test → run (FAIL) → fix → run (PASS) → revert fix → run (FAIL) → restore → run (PASS) → done.
❌ "I added a test" (red-green-red not actually verified).
✅ Re-read the spec → checklist each requirement → verify each → report any gaps.
❌ "Tests pass, phase complete."
✅ Subagent reports success → check `git diff` → verify changes are actually right → report actual state.
❌ Trust the subagent report.
ALWAYS before:
This rule applies to:
There are no shortcuts to verification.
Run the command. Read the output. THEN claim.
Non-negotiable.
| Claim | Verification command |
|---|---|
| "Flutter feature done" | flutter test test/<feature>/ + flutter analyze |
| "Functions deploy OK" | firebase functions:log --only <fn> shows no error within 5 minutes after deploy |
| "Firestore rules OK" | firebase emulators:exec --only firestore "npm test:rules" |
| "App release build OK" | flutter build apk --release (iOS build deferred per ADR-0002) |
| "BE Node tests pass" | npm test exit 0 + coverage didn't drop |