사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/mdsmithaustin/pstack --skill principle-prove-it-works시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Prove It Works
Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."
Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.
Check the real thing, not a proxy:
- Check process liveness directly, not indirectly through derived state
- Read the actual value, not a cached or derived representation
- When verification fails, suspect the observation method before suspecting the system
Account for the accepted scope
Check against the original accepted requirements. A plan, summary, or delegation cannot silently narrow them. Link each requirement to evidence or an explicit gap in the existing task record. An unmet requirement prevents a full completion claim. Preserve any backstop or judgment tags and record authorized scope changes separately. Reuse a runner's record when one exists.
When the work includes a threat model or security review, reconcile every declared threat with mitigation evidence at the threatened boundary. A claim of mitigation is not evidence. Record accepted risk with its authorized owner, transferred responsibility with its owner and evidence, or an open gap. Unresolved threats stay visible in the completion verdict.
Tie proof to the result
Record the artifact each check exercised, its revision when applicable, and the relevant environment. After combining changes, rerun checks for the affected paths on the integrated result. Separate passing branches do not prove their combination.
Run a named acceptance helper when the task or project requires it. If it cannot run, report the gap. Justify any replacement against the same acceptance criteria before treating it as equivalent.
Script the check when you can
The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.
Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill).
