verification-before-completion

Run verification commands and confirm output before claiming success. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs.

⭐9stars🔀0forks📁View on GitHub🕐Updated Jan 1, 2026

When & Why to Use This Skill

The 'Verification Before Completion' skill enforces a rigorous, evidence-based protocol for software development and AI agent tasks. It mandates the execution of fresh verification commands—such as unit tests, builds, and linting—to provide concrete proof of success before any work is claimed as finished. By eliminating assumptions and 'false success' reports, this skill significantly improves code reliability, reduces regressions, and ensures high-quality deployments.

Use Cases

  • Pre-Commit Validation: Ensuring all unit tests pass and the linter is error-free before committing code or opening a pull request to maintain repository integrity.
  • Red-Green Bug Fixing: Verifying a fix by running a regression test that fails without the fix and passes with it, providing absolute proof of resolution.
  • Build & Type Safety: Executing full build sequences and TypeScript compiler checks (tsc) after refactoring to ensure no hidden breaking changes were introduced.
  • AI Agent Quality Gate: Preventing AI agents from prematurely reporting task completion by requiring raw command output as evidence of success.
  • Requirement Checklist Verification: Systematically checking off project requirements against actual test results and environment states to ensure 100% compliance.
nameverification-before-completion
descriptionRun verification commands and confirm output before claiming success. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs.
version1.1.0

Verification Before Completion

Overview

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.

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

Skip any step = lying, not verifying

Common Verification Commands

Tests:

# Preferred: bun
bun test

# Alternative: npm
npm test

Build:

# Preferred: bun
bun run build

# Alternative: npm
npm run build

Lint:

# Preferred: bun
bun run lint

# Alternative: npm
npm run lint

Type check:

# Preferred: bun
bunx tsc --noEmit

# or: npx tsc --noEmit

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

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"
  • 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
"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

Why This Matters

From failure memories:

  • False claims broke trust
  • Undefined functions shipped - would crash
  • Missing requirements shipped - incomplete features
  • Time wasted on false completion → redirect → rework
  • Violates: "Honesty is a core value. If you lie, you'll be replaced."

When To Apply

ALWAYS before:

  • ANY variation of success/completion claims
  • ANY expression of satisfaction
  • ANY positive statement about work state
  • Committing, PR creation, task completion
  • Moving to next task
  • Delegating to agents

Rule applies to:

  • Exact phrases
  • Paraphrases and synonyms
  • Implications of success
  • ANY communication suggesting completion/correctness

The Bottom Line

No shortcuts for verification.

Run the command. Read the output. THEN claim the result.

This is non-negotiable.