GitHub's 17.4k-Star stop-slop Teaches LLMs to Strip AI Writing Tells

tom_doerr · x · 2026-09-21

The GitHub project stop-slop (17.4k stars, 1.3k forks) is a skill file for removing "AI tells" from prose, teaching Claude or any LLM to catch and eliminate predictable phrases, structural clichés, and rigid rhythmic patterns.

Structure:

Usage: add the folder as a skill in Claude Code; upload SKILL.md and references to Claude Projects; copy core rules into custom instructions; include SKILL.md in the system prompt for API calls, with references loaded on demand.

It catches throat-clearing openers, emphasis crutches, business jargon, all adverbs, vague declaratives, meta-commentary; binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, narrator-from-a-distance voice, and passive voice.

Original post →

More from coding & agent

coding & agent channel →