fluff-detector

SKILL.md

Verify that agents, commands, and skills are written for LLM consumption, not human readers. Every token should improve execution, not provide comfort or credibility.

Content that establishes credibility for humans but has no LLM value.

| "Inspired by X" | "Inspired by DHH's approach" | LLM can't retrieve by author | | "Based on X's methodology" | "Based on Martin Fowler's patterns" | Pure credibility signal | | "According to X" | "According to industry experts" | Appeal to authority | | "As recommended by" | "As recommended by Google" | No execution value |

檢測 LLM 工件中以人為本的內容。標記歸因、人物角色、冗餘解釋、營銷語言和裝飾元素，這些元素會浪費代幣而不會改善 LLM 行為。 來源：majesticlabs-dev/majestic-marketplace。

查看原文