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.

在宣布任何任务完成之前，实际验证结果。运行代码。 测试修复。检查输出。克劳德的训练优化了看似合理的外观 输出，未经验证的正确输出。该技能强制执行验证步骤 这不是自然而然的。没有证据就没有胜利。 来源：elliotjlt/claude-skill-potions。

查看原文