unslop

Rewrites text to remove AI writing patterns and restore natural human voice.

2|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/nseng-ai/ns --skill unslop-nseng-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: unslop
Source: https://github.com/nseng-ai/ns/tree/main/.agents/skills/unslop
Command: npx skills add https://github.com/nseng-ai/ns --skill unslop-nseng-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated and AI-assisted writing carries recognizable tells: puffery, em dash overuse, chatbot phrases, vague attributions, and formulaic structure. This Skill systematically detects and rewrites those patterns so text reads as natural human writing while preserving the original meaning and tone. ## Core Features & Use Cases - Pattern Detection and Rewriting: Scans text against 31 documented AI tells across content, language, style, filler, jargon, and plain-speech categories, then rewrites each instance. - Voice Restoration: Goes beyond deletion by adding opinions, varied sentence rhythm, first person where fitting, and concrete specifics so the result is not sterile. - Self-Audit Loop: Ends each pass by asking what still makes the text look machine-generated and fixing remaining tells. - Use Case: Paste a draft blog post or README section that was drafted with AI assistance and receive a version with plain vocabulary, active voice, no em dashes, and concrete statements instead of vague claims. ## Quick Start Ask the agent to apply the unslop skill to rewrite the attached draft and remove all AI writing patterns.

Frequently Asked Questions about unslop

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

FAQPage Schema
How do I remove AI writing patterns from a draft?

Apply the skill to the draft text. It scans for 31 documented AI tells across content, language, style, filler, and jargon categories, rewrites each instance while preserving meaning, then self-audits for remaining machine-generated signals.

What are common signs of AI-generated text?

Common tells include puffery like "pivotal moment", em dash overuse, chatbot phrases like "I hope this helps", vague attributions like "experts believe", rule-of-three structures, and abstract jargon like "leverage" or "tapestry".

Does rewriting AI text change the original meaning?

No. The process explicitly preserves meaning and matches the intended tone. It replaces patterns with plainer equivalents, cuts filler, and adds concrete specifics rather than altering the substance of the content.

Can this fix sterile or voiceless writing too?

Yes. Removing patterns is only half the job. The skill also adds soul by introducing opinions, varied sentence rhythm, first person where fitting, and specific details so the result does not read as flat or machine-neutral.

When should I not use automated AI-pattern removal?

Avoid it when the text requires strict formal register where first person or opinionated voice is inappropriate, or when quoted material must remain verbatim. The rewriting step intentionally changes phrasing and rhythm.