verification-before-completion
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
DollarDill · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add DollarDill/beads-superpowers --skill verification-before-completion技能说明
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
Verification Before Completion
Overview
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
The Gate Function
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
6. CLOSE: If this verification gates a bead closure, run `bd close <id> --reason "description with evidence from step 4"`
Skip any step = lying, not verifying
Agent-Filed Bead Discipline
When a skill files a bead for discovered/follow-up work (not planned work), stamp it so a human can triage risk at a glance.
- Title: prefix
[spec]ONLY if speculative. Confirmed beads keep clean titles. - Body/notes — always include this 3-field stamp:
Severity: Critical | Important | Minor Confidence: Confirmed | Speculative Evidence: <file:line / failing test / repro> (or: none) - Mechanical rule: evidence cited →
Confidence: Confirmed; no evidence →Confidence: Speculative. Applies at all severities. Never blocks filing (surface-and-mark — Production-Grade Doctrine). - What counts as evidence (claim-substantiating AND checkable, not "a string exists"):
- ✅
parser.ts:142 — returns null on empty input (fails t_parse_empty) - ❌
parser.ts — looks wrong
- ✅
- High-severity nudge: a
Critical/Importantbead filed without evidence MUST add one line:Why this severity w/o evidence: <reason>. - Priority (
-p) stays human-owned — do not infer priority from severity. - Honest limit: this disciplines the instruction surface, not every runtime bead.
Confidence: Confirmedis a falsifiable triage hint that lowers verification cost, not proof. The convention is forward-only — pre-existing beads stay unstamped.
Common Failures
| 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 |
| No security regression | SAST/audit tool if one exists (semgrep, bandit, npm/pip audit) → 0 new findings, AND diff review: no control weakened/removed/bypassed, no new sink. No tool? Use the "If Verification Cannot Run" path: record the manual diff-review as evidence, note no SAST available. | Tests pass (tests rarely cover security) |
If Verification Cannot Run
When no verification command exists (no test suite, CI down, external dependency unavailable):
- Record the gap:
bd note <id> "verification blocked: <reason>" - Create a blocker:
bd create "Set up verification for <feature>" -t taskandbd dep add <current-task> <new-task> - Document partial verification: Note what WAS verifiable (e.g., "linter passes, manual smoke test done, but no automated test suite exists")
- Never silently skip: A bead closed without verification evidence AND without a documented gap is worse than a bead left open
Red Flags - STOP
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
- About to commit/push/PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking "just this once"
- About to claim done while a requirement was quietly dropped, or a security regression remains unverified (tests passing ≠ security verified)
- Tired and wanting work over
- ANY wording implying success without having run verification
Rationalization Prevention
| 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 |
| "It's good enough to ship" | Production system, real users — no shortcut, no dropped requirement, no accepted security regression |
| "Different words so rule doesn't apply" | Spirit over letter |
Key Patterns
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 To Apply
ALWAYS before:
- ANY variation of success/completion claims
- ANY expression of satisfaction
- ANY posi