Checks whether work is truly complete before reporting success, committing changes, or creating a pull request. It runs the relevant checks, reads their full output, and ties status reports to current evidence.
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
Verifies the evidence before reporting that work is complete or a fix has succeeded. It selects a command that can establish the claim, runs it, and checks the full output, exit code, and number of failures before describing the status. Tests, builds, and code style checks are treated separately, with the appropriate evidence required for each. Requirements are checked individually. Changes made by another agent are also examined through their diff and verification results.
Use it when submitting corrected code, preparing a commit, or creating a PR. It helps you understand what has actually been verified and what problems remain, without treating earlier test results or an assumption that something should work as proof of completion.
Requires commands and an execution environment that can verify the work. Previous runs and partial checks do not count as evidence of current success. If the results do not support a claim, it reports the actual status and supporting evidence.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
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
| 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 |
| 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 |
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
ALWAYS before:
Rule applies to:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Clarifies the purpose, preferences, and constraints of a new feature or project through conversation. When useful, it offers mockups or temporary prototypes, then captures an agreed description or written design before implementation begins.
Examine superpowers session records to document repeated work, departures from plans, delays, and token usage. Produce an evidence-based report with file and line references, and prepare bug-report material when requested.
Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.
Carry out an existing implementation plan in one session, task by task. Verify each step with tests, record progress and decisions in a file, and finish with a review of all changes on the branch.
Finish completed development work by checking the full test suite and presenting integration choices: merge locally, create a Pull Request, or keep the branch. It carries out the selected path and handles workspace cleanup accordingly.
Evaluate code review feedback against the actual code, supported environments, and existing behavior. Clarify uncertain requests, respond with technical evidence, and implement valid changes one at a time with tests for each fix.