Stop Slop

A skill for removing AI tells from prose. It teaches the language model to catch and remove common patterns in AI-generated writing, resulting in more natural, human-like text.

What it does

AI writing often follows predictable patterns. This skill identifies and removes common tells—repetitive phrases, structural clichés, and sentence-level habits that make text sound artificial.

Core capabilities

Phrase removal – Eliminates throat-clearing openers, emphasis crutches, business jargon, all adverbs, vague declaratives, and meta-commentary. (See phrases.md)

Structural revision – Fixes binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, narrator-from-a-distance voice, and passive voice. (See structures.md)

Sentence-level rules – No Wh- sentence starters, no em dashes, no staccato fragmentation, no lazy extremes, and active voice required.

How it works

You provide a piece of text, and the skill applies the above rules to detect and rewrite problematic parts. The output is cleaner, more direct prose.

Scoring guide

Use the following 1–10 scales to evaluate the output:

A total below 35/50 indicates further revision is needed.