Strip predictable AI tells from prose - filler openers, adverbs, binary contrasts, em dashes, vague declaratives, and pull-quotes - with a checklist and a 50-point scoring rubric for revision.
---
name: stop-slop
description: Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
---
An editing pass that hunts and removes the patterns that make prose read as AI-generated.
## How to use
1. Apply the core rules: cut filler openers and adverbs, break formulaic structures (binary "not X but Y" contrasts, negative listings, rhetorical setups), and write in active voice with a human subject doing something.
2. Be specific over vague - name the actual thing instead of "the reasons are structural"; avoid lazy extremes like every/always/never.
3. Vary rhythm: mix sentence lengths, prefer two items over three, remove em dashes, and don't end every paragraph on a punchy one-liner.
4. Run the Quick Checks list, then score the draft 1-10 across Directness, Rhythm, Trust, Authenticity, and Density; revise if below 35/50. See `references/phrases.md`, `structures.md`, and `examples.md`.
Full skill & source: https://github.com/hardikpandya/stop-slop/tree/8da1f030185bdfe8471220585162991eaeb970e9