Get the FREE Ultimate OpenClaw Setup Guide →

verification-before-completion

Scanned
npx machina-cli add skill faulkdev/github-copilot-superpowers/verification-before-completion --openclaw
Files (1)
SKILL.md
5.1 KB

Verification Before Completion

[2026-02-01 CONSOLIDATION NOTE] This is the OBRA version (obra-verification-before-completion), which was promoted as the primary implementation due to:

  • More structured Copilot Completion Checklist (Requirements/Correctness/Quality/Verification)
  • Explicit "Why This Matters" context from failure memories
  • Agent delegation pattern guidance

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.

Copilot Completion Checklist

Requirements

  • Re-state what "done" means (from the user request)
  • Confirm each requirement is satisfied (link to files/lines if possible)

Correctness

  • Consider edge cases (inputs, nulls, errors)
  • Add regression tests when fixing bugs

Quality

  • Lint/format follows project rules
  • No debug prints/logs left behind unless requested
  • Minimal diff; clear naming

Verification commands (choose what fits repo)

  • Tests:
  • Lint:
  • Build:
  • Typecheck:

No fabricated verification

  • If you can't run commands, provide them and state you didn't execute them

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 Failures

ClaimRequiresNot Sufficient
Tests passTest command output: 0 failuresPrevious run, "should pass"
Linter cleanLinter output: 0 errorsPartial check, extrapolation
Build succeedsBuild command: exit 0Linter passing, logs look good
Bug fixedTest original symptom: passesCode changed, assumed fixed
Regression test worksRed-green cycle verifiedTest passes once
Agent completedVCS diff shows changesAgent reports "success"
Requirements metLine-by-line checklistTests 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

ExcuseReality
"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 24 failure memories:

  • Your human partner said "I don't believe you" - trust broken
  • 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.

Source

git clone https://github.com/faulkdev/github-copilot-superpowers/blob/integrate-obra-superpowers/.github/skills/verification-before-completion/SKILL.mdView on GitHub

Overview

Claiming completion without verification is dishonest, not efficient. This skill enforces running verification commands (tests, lint, build, typecheck) and citing verifiable outputs before asserting success.

How This Skill Works

Identify the command that proves the claim (tests, lint, build, typecheck). Run the FULL command in a fresh context. Read the full output and exit code, then verify whether the results substantiate the claim; only then state status with evidence.

When to Use It

  • Before committing or pushing changes
  • Before opening a pull request or status update
  • After implementing a feature or bug fix and running verification commands
  • When reporting success to teammates or documenting progress
  • Before marking a milestone as done in release notes or project docs

Quick Start

  1. Step 1: Identify the verification command that proves the claim (tests, lint, build, typecheck)
  2. Step 2: Run the FULL command in a fresh environment and collect outputs
  3. Step 3: Read the outputs, confirm exit codes and failures, then claim success only with evidence

Best Practices

  • Restate what 'done' means from the user request and verify each requirement (link to files/lines if possible)
  • Consider edge cases and add regression tests for fixes
  • Enforce quality: lint/formatting rules, remove debug prints/logs, keep diffs minimal and naming clear
  • Use explicit verification commands (tests, lint, build, typecheck) and rely on fresh outputs
  • If you cannot run commands, provide the commands and clearly state you didn’t execute them

Example Use Cases

  • Run the test suite and confirm 0 failures, then claim tests pass with evidence from the test runner
  • Execute lint with 0 errors and include the lint output as verification
  • Perform a full build that exits cleanly (exit code 0) and cite the build log
  • Validate a bug fix with a regression test that reproduces the original symptom and passes after the fix
  • Document completion only after obtaining fresh verification outputs; avoid claiming success without them

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers