개요
LLM(Claude)를 위해 설계된 기술 문서는 일반적인 AI 글쓰기 흔적을 탐지하고 제거하는 데 사용되며, 문구, 구조 라인 및 문장 수준 규칙을 비활성화하고, 프로세스 품질을 평가하는 등급 시스템을 제공합니다.
README 미리보기
# Stop Slop\n\nA skill for removing AI tells from prose.\n\n\n\n## What this is\n\nAI writing has patterns. Predictable phrases, structures, rhythms. This skill teaches Claude (or any LLM) to catch and remove them.\n\n## Skill Structure\n\n```\nstop-slop/\n├── SKILL.md # Core instructions\n├── references/\n│ ├── phrases.md # Phrases to remove\n│ ├── structures.md # Structural patterns to avoid\n│ └── examples.md # Before/after transformations\n├── README.md\n└── LICENSE\n```\n\n## Quick start\n\n**Claude Code:** Add this folder as a skill.\n\n**Claude Projects:** Upload `SKILL.md` and reference files to project knowledge.\n\n**Custom instructions:** Copy core rules from `SKILL.md`.\n\n**API calls:** Include `SKILL.md` in your system prompt. Reference files load on demand.\n\n## What it catches\n\n**Banned phrases** - Throat-clearing openers, emphasis crutches, business jargon, all adverbs, vague declaratives, meta-commentary. See `references/phrases.md`.\n\n**Structural clichés** - Binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, narrator-from-a-distance voice, passive voice. See `references/structures.md`.\n\n**Sentence-level rules** - No Wh- sentence starters, no em dashes, no staccato fragmentation, no lazy extremes, active voice required.\n\n## Scoring\n\nRate 1-10 on each dimension:\n\n| Dimension | Question |\n|-----------|----------|\n| Directness | Statements or announcements? |\n| Rhythm | Varied or metronomic? |\n| Trust | Respects reader intelligence? |\n| Authenticity | Sounds human? |\n| Density | Anything cuttable? |\n\nBelow 35/50: revise.\n\n## Author\n\n[Hardik Pandya](https://hvpandya.com)\n\n## License\n\nMIT. Use freely, share widely.\n