agentsclimarketplace

Verification before completion

Skill a-ariff/ariff-claude-plugins/plugins/verification-before-completion/skills/verification-before-completion

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

Install
npx -y skills add a-ariff/ariff-claude-plugins --skill verification-before-completion

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Never claim completion without fresh verification evidence

SKILL.md

2.4 KB, as published. Nobody here has run it

Verification Before Completion

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the command in THIS message, you cannot claim it passes.

The Gate

Before claiming ANY success:

1. IDENTIFY → What command proves this claim?
2. RUN → Execute the FULL command
3. READ → Full output, check exit code
4. VERIFY → Does output confirm the claim?
5. CLAIM → Only now, with evidence

Skip ANY step = lying, not verifying.

What Requires Verification

ClaimRequiresNOT Sufficient
"Tests pass"Test output: 0 failures"Should pass", previous run
"Build works"Build output: exit 0Linter passing
"Bug fixed"Test of original symptom"Code changed"
"Linter clean"Linter output: 0 errors"Looks right"
"Feature complete"All requirements checked"Tests pass"

Red Flags - STOP

If you catch yourself:

  • Using "should", "probably", "seems to"
  • Saying "Great!", "Perfect!", "Done!" before running verification
  • About to commit without fresh test run
  • Thinking "just this once"
  • Feeling tired and wanting to be done

STOP. Run the verification.

Rationalization Prevention

You ThinkReality
"Should work now"RUN IT
"I'm confident"Confidence ≠ evidence
"Just this once"No exceptions
"Linter passed"Linter ≠ tests
"I'm tired"Exhaustion ≠ excuse

Correct Patterns

Tests:

✅ [run test] → See "34/34 pass" → "All tests pass"
❌ "Tests should pass now"

Build:

✅ [run build] → See "exit 0" → "Build passes"
❌ "Build looks good"

Requirements:

✅ Re-read requirements → Check each → Report gaps
❌ "Tests pass so it's complete"

Why This Matters

From actual failures:

  • User said "I don't believe you" - trust broken
  • Undefined functions shipped - would crash at runtime
  • Missing requirements - incomplete features
  • Time wasted on false completion → redirect → rework

Bottom Line

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

This is non-negotiable.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.