prove-it

SKILL.md

Claude generates code by pattern-matching on training data. Something can look syntactically perfect, follow best practices, and still be wrong. The model optimizes for "looks right" not "works right." Verification is a separate cognitive step that must be explicitly triggered. This skill closes the loop between implementation and proof.

1. Generation vs Execution I generate code but don't run it. I predict what it would do based on patterns. My confidence comes from "this looks like working code I've seen" not from "I executed this and observed the result."

2. Training Signal Mismatch My training optimizes for plausible next-token prediction, not outcome verification. Saying "Done!" feels natural. Verifying feels like extra work.

작업 완료를 선언하기 전에 실제로 결과를 확인하세요. 코드를 실행하세요. 수정 사항을 테스트하십시오. 출력을 확인하십시오. Claude의 훈련은 그럴듯해 보이는 것에 최적화되어 있습니다. 검증된 올바른 출력이 아닌 출력. 이 스킬은 검증 단계를 강제합니다. 그것은 자연스럽게 나오지 않습니다. 증거 없이는 승리를 거둘 수 없습니다. 출처: elliotjlt/claude-skill-potions.

원본 보기