obra/superpowers

verification-before-completion

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

All-time #241 Trending #285 Hot #6560 First seen Jan 19, 2026
8-week activity · all time api

Installation

$ npx skills add obra/superpowers --skill verification-before-completion

Summary

  • Enforce verification commands before claiming work completion, fixes, or test passes—no success assertions without fresh evidence.
  • Requires running the actual verification command (not assumptions or partial checks) and confirming output before making any completion or correctness claims Applies to all success-related statements: test passes, builds succeeding, bugs fixed, requirements met, regressions verified, and agent task completion Blocks common shortcuts like trusting agent reports, relying on linter passes as build proof, or using confidence/assumptions instead of actual command output Includes a five-step gate function: identify the proof command, run it fresh, read full output and exit code, verify the claim matches evidence, then state the result with evidence attached

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Security audits

Partner security reviews for this skill.

agent-trust-hub SAFE

Analyzed Feb 17, 2026

This skill acts as a behavioral policy that enforces a 'verification-first' workflow, requiring the agent to prove task completion through command execution and output analysis. It contains no malicious code, external dependencies, or data exfiltration risks.

snyk LOW

Analyzed Jul 2, 2026

No issues detected.

socket Score 0.9000 · 0 alerts

Analyzed Mar 18, 2026

  • license 1
  • maintenance 1
  • quality 0.9
  • supply chain 1
  • vulnerability 1

0 alerts

Also in this package

Other skills from obra/superpowers · top by installs.

npx skills add obra/superpowers

Browse all from obra/superpowers

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 283.3K
License LICENSE
Default branch main
Open issues 125
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,646 B
  • docs SUMMARY.md 263 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 204,500 installs

SKILL.md

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