verification-before-completion
obra/superpowers
Verify work with fresh evidence before claiming completion—no assertions without proof.
What is verification-before-completion?
This skill enforces a discipline of running verification commands and confirming their output before making any claims about work being complete, fixed, or passing. Use it whenever you're about to commit, create a PR, or move to the next task to ensure you're basing assertions on actual evidence, not assumptions.
- Requires running full verification commands fresh before any completion claims
- Enforces a gate function: identify the proof command, run it, read output, verify it matches the claim
- Prevents common failures like trusting partial checks, previous runs, or agent success reports without independent verification
- Flags rationalization patterns ("should work", "probably", "I'm confident") that bypass evidence
- Applies to all success claims, satisfaction expressions, and positive work-state statements
How to install verification-before-completion
npx skills add https://github.com/obra/superpowers --skill verification-before-completionHow to use verification-before-completion
- 1.Before making any completion or success claim, identify what command proves that claim
- 2.Run the full verification command fresh (not from memory or previous runs)
- 3.Read the complete output, check the exit code, and count any failures or errors
- 4.Verify that the output actually confirms your claim—if not, state the actual status with evidence instead
- 5.Only after confirmation, make your claim and include the evidence in your statement
Use cases
- Before committing code, run the full test suite and confirm zero failures in fresh output
- Before creating a PR, verify the build exits with code 0 and linter shows zero errors
- Before claiming a bug is fixed, re-run the original failing test and confirm it now passes
- Before delegating to an agent, verify their reported success by checking the actual VCS diff and running verification independently
- Before moving to the next task, re-read requirements and verify each one against actual output, not assumptions
- Developers committing code or creating pull requests
- QA engineers verifying fixes and regressions
- Anyone delegating work to AI agents and needing to validate results
- Teams enforcing code quality gates before merge
verification-before-completion FAQ
Confidence is not evidence. You must run the verification command and see the output. Exhaustion, time pressure, or confidence do not override this requirement.
No. Linter passing does not prove compilation succeeds. Each claim requires its specific verification command run fresh. Partial checks prove nothing.
No. Always verify independently by checking the actual VCS diff and running verification commands yourself. Agent reports are not evidence.
Yes. The rule applies to the spirit, not just exact phrases. Any wording implying success without fresh verification evidence violates the rule.
Write the test → run it (must fail on unfixed code) → apply the fix → run it (must pass) → revert the fix → run it (must fail again) → restore the fix. Only this cycle proves the test actually catches the bug.
Full instructions (SKILL.md)
Source of truth, from obra/superpowers.
name: verification-before-completion description: 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
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
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests 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
| Excuse | Reality |
|---|---|
| "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
Related skills
More from obra/superpowers and the wider catalog.
writing-plans
Create detailed implementation plans for multi-step coding tasks before writing code.
writing-skills
Test-Driven Development for AI agent skill documentation—write tests, watch agents fail, document the fix.
brainstorming
Explore intent and design before building—turn ideas into approved specs through structured dialogue.
diagnosing-superpowers
Diagnose superpowers session failures by reading transcripts and building evidence-backed reports.
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to make any prose clearer, stronger, and more professional.
commodities-quote
Retrieve real-time commodity price quotes using Octagon MCP. Use when checking current commodity prices, analyzing day ranges, comparing to moving averages, and tracking precious metals, energy, and agricultural commodity prices.