deslop

Rewrite prose to remove predictable AI writing patterns and score drafts on a rubric.

2|1|Updated Mar 7, 2026
One-click install
npx skills add https://github.com/stephenturner/skills --skill deslop-stephenturner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deslop
Source: https://github.com/stephenturner/skills/tree/main/deslop
Command: npx skills add https://github.com/stephenturner/skills --skill deslop-stephenturner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It removes predictable AI writing tells such as filler phrases, formulaic structures, vague declaratives, and other “machine-like” prose patterns so your writing sounds authored by a specific human.

Core Features & Use Cases

  • AI tell removal and rewrite guidance: targets throat-clearing, emphasis crutches, binary/negative-list patterns, dramatic fragmentation, shallow analyses, and formatting tells that commonly appear in AI output.
  • Style adjustment by writing context: applies different register guidance for blog/newsletter voice versus scientific/technical “we” voice, including how to handle passive voice and actor clarity.
  • Editing support with a scoring rubric: rates drafts 1–10 across directness, rhythm, trust, authenticity, and density, guiding what to revise next.

Quick Start

Use the deslop skill to rewrite your draft by asking: “Deslop this text and score it on the deslop rubric, focusing on directness, rhythm, trust, authenticity, and density.”

Frequently Asked Questions about deslop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I rewrite AI-generated text to sound more human?

To rewrite AI-generated text to sound more human, remove filler phrases, formulaic structures, and vague declaratives. This process eliminates predictable machine-like patterns, adjusting prose style to ensure your writing sounds authored by a specific human.

What are common AI writing tells and how do I remove them?

Common AI writing tells include throat-clearing, emphasis crutches, binary patterns, and dramatic fragmentation. You remove them by applying checklist-based cleanup rules that target these specific structures, replacing shallow analyses with authentic prose.

Can I use this to edit scientific writing without losing technical accuracy?

Yes, you can edit scientific writing by applying a specific style adjustment for the scientific and technical 'we' voice. This provides register guidance that handles passive voice and actor clarity appropriately while removing AI tells from technical drafts.

How do I score my draft for human authenticity and directness?

You score drafts for human authenticity and directness using a rubric that rates text 1–10 across five dimensions: directness, rhythm, trust, authenticity, and density. This rubric guides what specific elements to revise next.

Does this editing approach work for blog posts and newsletters?

Yes, this editing approach works for blog posts and newsletters by applying distinct style adjustment guidance for blog and newsletter voice. It targets the specific formatting tells and prose patterns that commonly appear in AI-generated content marketing.

When should I avoid using automated prose cleanup tools?

You should avoid using automated prose cleanup tools when your draft requires preserving highly specific formatting structures or intentional stylistic fragmentation. These tools target predictable patterns, so they may alter deliberate dramatic structures or specialized technical phrasing.