SuperAPI AI Directory

verification-before-completion

General & other

View repository

Updated 10-16 09:56

About this skill

Verify before completion

Overview

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

Core principle: Always evidence first, then claims.

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 verification command in this message, you cannot claim it passes.

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 Requires Insufficient
Tests pass Test command output: 0 failures Ran before, "should pass"
Linter clean Linter output: 0 errors Partial check, extrapolation
Build succeeds Build command: exit 0 Linter passes, logs look normal
Bug fixed Original symptom test: passes Code changed, assumed fixed
Regression tests effective Red-green cycle verified Tests pass once
Agent completed VCS diff shows changes Agent reports "success"
Requirements satisfied Line-by-line checklist Tests pass

Danger signs - stop

  • Using "should", "probably", "seems"
  • Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
  • Preparing to commit/push/PR without verification
  • Trusting an agent's success report
  • Relying on partial verification
  • Thinking "just this once"
  • Tired and wanting to finish work
  • Any wording that implies success without running verification

Prevent rationalization

Excuse Reality
"It should work now" Run verification
"I am confident" Confidence ≠ evidence
"Just this once" No exceptions
"The linter passed" Linter ≠ compiler
"The agent said it succeeded" Independent verification
"I am tired" Tiredness ≠ excuse
"Partial checking is enough" Partial checking proves nothing
"I changed the wording, so the rule does not 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 24 failure memories:

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

When to apply

Always apply before the following:

  • Any form of success/completion claim
  • Any expression of satisfaction
  • Any positive statement about work status
  • Submitting, creating a PR, completing a task
  • Moving to the next task
  • Delegating to agents

The rules apply to:

  • Exact phrases
  • Paraphrases and synonymous expressions
  • Implications of success
  • Any communication implying completion/correctness

Bottom line

There are no shortcuts to verification.

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

This is non-negotiable.