unslop

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

Updated Sep 2, 2026
One-click install
npx skills add https://github.com/jnyross/pstack-muse --skill unslop-jnyross
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: unslop
Source: https://github.com/jnyross/pstack-muse/tree/main/skills/unslop
Command: npx skills add https://github.com/jnyross/pstack-muse --skill unslop-jnyross

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 detects 31 specific patterns across content, language, style, and jargon, then rewrites the text to read like a human wrote it. ## Core Features & Use Cases - Pattern Detection and Rewriting: Scans text for 31 cataloged AI tells including promotional language, rule-of-three structures, synonym cycling, and abstract metaphor nouns, then rewrites each instance while preserving meaning and tone. - Voice Restoration: Goes beyond deletion by adding opinions, varied sentence rhythm, first person where appropriate, and specific concrete details so the result is not sterile. - Self-Audit Loop: Finishes with a check asking what still makes the text obviously AI-generated and fixes remaining tells. - Use Case: You drafted a product announcement with an AI assistant and it reads like generic marketing copy. Run this Skill to strip the puffery, replace vague claims with specifics, and produce a version that sounds like a person wrote it. ## Quick Start Use the unslop skill to rewrite this blog post draft so it no longer reads as AI-generated.

Frequently Asked Questions about unslop

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

FAQPage Schema
How do I make AI-generated text sound human?

Run the text through a rewriting pass that targets known AI tells: cut puffery and promotional adjectives, replace vague attributions with named sources, remove em dashes and chatbot phrases, and vary sentence rhythm. This Skill applies 31 such patterns automatically.

What are the most common AI writing tells to remove?

The most common tells are words like delve, crucial, and tapestry, em dash overuse, rule-of-three structures, superficial -ing phrases like highlighting or showcasing, and closers like I hope this helps. The Skill catalogs 31 patterns across content, language, style, and jargon.

Does removing AI patterns change the meaning of my text?

No. The rewriting process preserves meaning and matches the intended tone while replacing flagged patterns. It substitutes plain concrete words for jargon and restructures sentences without altering the underlying claims or facts.

Why does my edited text still sound robotic after removing AI words?

Removing patterns is only half the job; sterile voiceless writing is also an AI tell. The fix is adding soul: opinions, varied sentence length, first person where it fits, and specific concrete details instead of neutral summaries.

When should I not use automated AI-tell removal?

Avoid it when the text is a direct quote, legal language, or technical specification where exact wording matters and must not be paraphrased. It is designed for prose like articles, docs, and emails, not verbatim source material.