skills/verification-before-completion/SKILL.md
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
npx skillsauth add schlenks/superpowers-bd verification-before-completionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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
When frontend code is modified and browser tools are available, visual verification is part of the gate function. Triggers when: browser tools exist, frontend files changed (.tsx, .jsx, .vue, .svelte, .css), dev server running. Skip silently if not applicable.
See references/visual-verification.md for full protocol.
When verification fails, don't just report — fix and re-verify:
IF verification fails:
1. CREATE gap-fix task
2. CREATE re-verification task (blocked by fix)
3. WAIT for gap fix completion
4. RUN re-verification
5. IF still fails AND attempt < 3: → Increment attempt, GOTO step 1
6. IF still fails AND attempt >= 3: → ESCALATE to human
See references/gap-closure-protocol.md for TaskCreate blocks and attempt tracking.
Before making ANY completion claim, create a verification task:
TaskCreate: "Verify: [specific claim]"
description: "Evidence required: [verification command]. Must capture command output and exit code."
activeForm: "Verifying [claim]"
ENFORCEMENT:
completed without evidence in the conversation| 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 | | UI renders correctly | Visual smoke test: page loads, no console errors | "Code looks right", build passes |
Using "should", "probably", "seems to". Expressing satisfaction before verification ("Great!", "Perfect!", "Done!"). About to commit/push/PR without verification. Trusting agent success reports. Relying on partial verification. Thinking "just this once". ANY wording implying success without having run verification.
| 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 |
references/visual-verification.md: Full visual/frontend verification protocolreferences/gap-closure-protocol.md: Gap-fix → re-verify → escalate enforcementreferences/key-patterns-examples.md: Verification patterns with examplesreferences/why-this-matters.md: Context from failure memoriesreferences/when-to-apply.md: When verification is requiredreferences/SKILL.test.md: Pressure test scenariostools
Use when converting a Superpowers-BD implementation plan or Shortcut story into a beads epic with dependency-aware child tasks
development
Use when the user asks for /cr-style review of local changes, commits, a branch diff, or a GitHub PR outside subagent-driven development
development
Use when you have a spec or requirements for a multi-step task, before touching code
tools
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions