Top AI Product

stop-slop is a Claude Code skill with one job: catch and remove the patterns that make AI writing recognizable as AI writing. Add it as a skill, drop it in a Claude Project, or paste it into an API system prompt, and it rewrites against a specific list of tells.

## What it bans

Throat-clearing openers. Emphasis crutches. Business jargon. All adverbs. Vague declaratives. Meta-commentary. Structurally it kills binary contrasts (“it’s not X, it’s Y”), negative listings, dramatic one-line fragments, rhetorical setups, and the detached “narrator-from-a-distance” voice. Core rule: active voice, every sentence with a human subject doing something, “you” instead of “people.”

## Why it matters

As AI-generated text floods every channel, the tells become a credibility tax — readers pattern-match “this was written by a bot” and disengage. A reusable skill that systematically removes those markers is the editing layer the AI-writing stack has been missing. It’s also a sharp reverse-engineering of what AI slop actually is: read the banned list and you have a checklist for spotting machine prose anywhere.