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 |

LLM 아티팩트에서 인간 중심 콘텐츠를 감지합니다. LLM 행동을 개선하지 않고 토큰을 낭비하는 속성, 페르소나, 중복 설명, 마케팅 언어 및 장식 요소에 플래그를 지정합니다. 출처: majesticlabs-dev/majestic-marketplace.

원본 보기