New to Claude Skills? Learn how to install them →

obra on GitHub

Verification Before Completion

Free

Ensure claims of completion are backed by evidence.

by obra270.3k stars on obra/superpowers
2 views
Updated Jul 28, 2026
Get this skill

Free · Opens the source repo

What Verification Before Completion does

The Verification Before Completion skill emphasizes the importance of validating work before making any claims of completion or correctness. It operates on the fundamental principle that no assertion of success should be made without fresh verification evidence. This skill is particularly useful for developers and teams who want to maintain high standards of quality and accountability in their work processes. By following a structured approach to verification, users can minimize errors and enhance the reliability of their claims.

The skill outlines a clear process that includes identifying the necessary verification commands, executing them fully, and analyzing the output before making any claims. It encourages a disciplined mindset where every claim is substantiated by concrete evidence, effectively reducing the risk of miscommunication and misunderstandings within teams. This is especially crucial in collaborative environments where multiple stakeholders rely on accurate reporting of progress and status.

In addition to preventing premature claims, the skill also highlights common pitfalls and red flags that can lead to verification failures. By recognizing these patterns and adhering to the outlined rules, users can foster a culture of thoroughness and precision. This approach not only improves individual accountability but also contributes to the overall integrity of the development process, ensuring that all team members are aligned and informed.

Ultimately, Verification Before Completion is designed for developers, QA engineers, and project managers who prioritize quality assurance and wish to establish a rigorous verification routine. By integrating this skill into their workflow, teams can enhance their operational effectiveness and reduce the likelihood of regressions or undetected issues in their code.

When to use it

Use this skill whenever you are about to claim that work is complete, fixed, or passing, particularly before committing or creating pull requests.

When not to use it

This skill may not be necessary for informal projects or when working in environments where verification is already inherently enforced or understood.

What you can build with it

Before Committing Code

Always run verification commands to confirm that the code is functioning as expected before making a commit.

Creating Pull Requests

Use this skill to ensure that all tests pass and that you have evidence to support your claims of completion before submitting a PR.

Quality Assurance Checks

Implement this skill in QA processes to ensure that all assertions about code quality are substantiated by actual test results.

How to install Verification Before Completion

View source

1. Install with the skills CLI

npx skills add obra/superpowers/verification-before-completion --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by obra

Verification Before Completion

Overview

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

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

Frequently asked questions about Verification Before Completion

Similar skills