Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from repo
Enforces running actual verification commands before claiming tests pass, builds succeed, or bugs are fixed.
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
SKILL.md
1---2name: verification-before-completion3description: 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 always4---56# Verification Before Completion78## Overview910Claiming work is complete without verification is dishonesty, not efficiency.1112**Core principle:** Evidence before claims, always.1314**Violating the letter of this rule is violating the spirit of this rule.**1516## The Iron Law1718```19NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE20```2122If you haven't run the verification command in this message, you cannot claim it passes.2324## The Gate Function2526```27BEFORE claiming any status or expressing satisfaction:28291. IDENTIFY: What command proves this claim?302. RUN: Execute the FULL command (fresh, complete)313. READ: Full output, check exit code, count failures324. VERIFY: Does output confirm the claim?33- If NO: State actual status with evidence34- If YES: State claim WITH evidence355. ONLY THEN: Make the claim3637Skip any step = lying, not verifying38```3940## Common Failures4142| Claim | Requires | Not Sufficient |43|-------|----------|----------------|44| Tests pass | Test command output: 0 failures | Previous run, "should pass" |45| Linter clean | Linter output: 0 errors | Partial check, extrapolation |46| Build succeeds | Build command: exit 0 | Linter passing, logs look good |47| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |48| Regression test works | Red-green cycle verified | Test passes once |49| Agent completed | VCS diff shows changes | Agent reports "success" |50| Requirements met | Line-by-line checklist | Tests passing |5152## Red Flags - STOP5354- Using "should", "probably", "seems to"55- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)56- About to commit/push/PR without verification57- Trusting agent success reports58- Relying on partial verification59- Thinking "just this once"60- Tired and wanting work over61- **ANY wording implying success without having run verification**6263## Rationalization Prevention6465| Excuse | Reality |66|--------|---------|67| "Should work now" | RUN the verification |68| "I'm confident" | Confidence ≠ evidence |69| "Just this once" | No exceptions |70| "Linter passed" | Linter ≠ compiler |71| "Agent said success" | Verify independently |72| "I'm tired" | Exhaustion ≠ excuse |73| "Partial check is enough" | Partial proves nothing |74| "Different words so rule doesn't apply" | Spirit over letter |7576## Key Patterns7778**Tests:**79```80✅ [Run test command] [See: 34/34 pass] "All tests pass"81❌ "Should pass now" / "Looks correct"82```8384**Regression tests (TDD Red-Green):**85```86✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)87❌ "I've written a regression test" (without red-green verification)88```8990**Build:**91```92✅ [Run build] [See: exit 0] "Build passes"93❌ "Linter passed" (linter doesn't check compilation)94```9596**Requirements:**97```98✅ Re-read plan → Create checklist → Verify each → Report gaps or completion99❌ "Tests pass, phase complete"100```101102**Agent delegation:**103```104✅ Agent reports success → Check VCS diff → Verify changes → Report actual state105❌ Trust agent report106```107108## Why This Matters109110From 24 failure memories:111- your human partner said "I don't believe you" - trust broken112- Undefined functions shipped - would crash113- Missing requirements shipped - incomplete features114- Time wasted on false completion → redirect → rework115- Violates: "Honesty is a core value. If you lie, you'll be replaced."116117## When To Apply118119**ALWAYS before:**120- ANY variation of success/completion claims121- ANY expression of satisfaction122- ANY positive statement about work state123- Committing, PR creation, task completion124- Moving to next task125- Delegating to agents126127**Rule applies to:**128- Exact phrases129- Paraphrases and synonyms130- Implications of success131- ANY communication suggesting completion/correctness132133## The Bottom Line134135**No shortcuts for verification.**136137Run the command. Read the output. THEN claim the result.138139This is non-negotiable.140