SuperAPI AI Directory

verification-before-completion

General & other

View repository

Updated 10-16 08:46

About this skill

Verify Before Completion

Overview

Claiming work is complete without verification is dishonest, not efficient.

Core principle: Evidence precedes claims, always.

**Violating the letter of this rule is violating the spirit of this rule. **

Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you have not run the validation command in this message, you cannot claim it passed.

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 Failures

Claim Required Not Enough
Tests pass Test command output: 0 failures Last run, "should pass"
Lint clean Linter output: 0 errors Partial investigation, inference
Build succeeds Build command: exit 0 Linter passes, logs look good
Bug fixed Test original symptom: pass Code changed, assumed fixed
Regression test works Red-green cycle verified Test passes once
Agent completes VCS diff shows changes Agent reports "success"
Requirements met Line-by-line checklist Tests pass

Red Flags - Stop

  • Using "should", "probably", "seems"
  • Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
  • About to work/labor/PR, consuming verification
  • Trusting agent success reports
  • Relying on partial verification
  • Thinking "just this once"
  • Tired and wanting to end work
  • Any wording that implies success without running verification

Rationalization Prevention

Excuse Reality
"It should work now" Run verification
"I'm confident" Confidence ≠ evidence
"Just this once" No exceptions
"Linter passes" Linter ≠ compiler
"The agent said success" Independent verification
"I'm tired" Exhaustion ≠ excuse
"A partial check is enough" A partial check proves nothing
"Different words, so the 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 test (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

24 failure memories:

  • Your human partner said "I don't believe you" - trust broken
  • Undefined function shipped - will crash
  • Missing delivered requirements - incomplete functionality
  • Time wasted on incorrect completion → redirection → rework
  • Violation: "Honesty is a core value. If you lie, you will be replaced."

When to apply

**Always before:**

  • Any change in success/completion claims
  • Any expression of satisfaction
  • Any positive statement about work status
  • Commitments, PR creation, task completion
  • Moving to the next task
  • Delegating to an agent

Rules apply to:

  • Exact phrases
  • Paraphrases and synonyms
  • Impact of success
  • Any communication indicating completion/correctness

Bottom line

**There are no shortcuts to verification.**

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

This is non-negotiable.