unslop

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

5|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/nuggocto/dotfiles --skill unslop-nuggocto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: unslop
Source: https://github.com/nuggocto/dotfiles/tree/main/opencode/skills/unslop
Command: npx skills add https://github.com/nuggocto/dotfiles --skill unslop-nuggocto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated and AI-assisted writing carries recognizable tells: puffery, vague attributions, chatbot phrases, formulaic structures, and jargon that make text feel machine-made. This Skill systematically detects and rewrites those patterns so the output reads like a human wrote it. ## Core Features & Use Cases - Pattern detection and rewriting: Scans text against 31 documented AI tells across content, language, style, filler, and jargon categories, then rewrites while preserving meaning and tone. - 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: After rewriting, asks what still makes the text obviously AI-generated and fixes remaining tells. - Use Case: Paste a draft blog post or documentation page full of phrases like "delve into the vibrant landscape" and "it's important to note that", and get back a tightened version with plain words, active voice, and concrete facts. ## Quick Start Ask the assistant to unslop this draft and remove all AI writing patterns while keeping the original meaning.

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?

Run the text through the unslop process: scan for the 31 documented patterns, rewrite each instance while preserving meaning, then add human voice through opinions, varied rhythm, and specifics. Finish with a self-audit asking what still looks machine-generated.

What are common signs of AI-generated text?

Common tells include puffery like "pivotal moment", vague attributions like "experts believe", superficial -ing phrases, rule-of-three structures, chatbot closers like "I hope this helps", and abstract jargon such as "leverage", "landscape", and "tapestry".

Does removing AI phrases change the meaning of my text?

No. The rewriting step explicitly preserves meaning and matches the intended tone. Patterns are replaced with plainer equivalents, such as "utilize" becoming "use", and vague claims are either sourced or deleted rather than altered in substance.

Why does my text still sound robotic after removing buzzwords?

Cutting patterns is only half the job; sterile, voiceless writing is equally obvious. Add soul by stating opinions, varying sentence length, using first person where it fits, and replacing generic statements with specific facts or numbers.

When should I not use this editing approach?

Avoid it when strict formal register is required, such as legal filings or compliance documents where first person and informal rhythm are inappropriate. The method targets prose meant to read as human-written, not templated or regulated text.