verification-before-completion — official verification-before-completion, superpowers, official, ide skills, Claude Code, Cursor, Windsurf

Verified
v1.0.0
GitHub

About this Skill

Essential for Code Integrity Agents that prevent premature completion claims and ensure technical accuracy. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

obra obra
[70.9k]
[5444]
Updated: 3/5/2026

Agent Capability Analysis

The verification-before-completion skill by obra is an open-source official AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Essential for Code Integrity Agents that prevent premature completion claims and ensure technical accuracy.

Core Value

Enforces the Iron Law of requiring fresh verification evidence before any completion claims, preventing false assertions about work being complete, fixed, or passing. It mandates running verification commands and confirming output before committing or creating PRs, establishing evidence before assertions as a core principle.

Capabilities Granted for verification-before-completion

Validating test suite results before PR creation
Confirming build success before deployment claims
Verifying bug fixes before marking issues resolved
Ensuring code quality metrics pass before completion assertions

! Prerequisites & Limits

  • Requires access to verification command execution
  • Needs output analysis capabilities
  • Depends on available testing/validation frameworks
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

verification-before-completion

Install verification-before-completion, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command...

SKILL.md
Readonly

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 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.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is verification-before-completion?

Essential for Code Integrity Agents that prevent premature completion claims and ensure technical accuracy. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

How do I install verification-before-completion?

Run the command: npx killer-skills add obra/superpowers/verification-before-completion. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for verification-before-completion?

Key use cases include: Validating test suite results before PR creation, Confirming build success before deployment claims, Verifying bug fixes before marking issues resolved, Ensuring code quality metrics pass before completion assertions.

Which IDEs are compatible with verification-before-completion?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for verification-before-completion?

Requires access to verification command execution. Needs output analysis capabilities. Depends on available testing/validation frameworks.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add obra/superpowers/verification-before-completion. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use verification-before-completion immediately in the current project.

Related Skills

Looking for an alternative to verification-before-completion or another official skill for your workflow? Explore these related open-source skills.

View All

flags

Logo of facebook
facebook

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

243.6k
0
Developer

extract-errors

Logo of facebook
facebook

Use when adding new error messages to React, or seeing unknown error code warnings.

243.6k
0
Developer

fix

Logo of facebook
facebook

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

243.6k
0
Developer

flow

Logo of facebook
facebook

Use when you need to run Flow type checking, or when seeing Flow type errors in React code.

243.6k
0
Developer