unslop

Rewrites prose to remove AI writing patterns and add human voice.

20|2|Updated May 16, 2026
One-click install
npx skills add https://github.com/reddb-io/red-skills --skill unslop-reddb-io
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: unslop
Source: https://github.com/reddb-io/red-skills/tree/main/plugins/dev/skills/productivity/unslop
Command: npx skills add https://github.com/reddb-io/red-skills --skill unslop-reddb-io

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated drafts carry recognizable tells like puffery, em dash overuse, chatbot phrases, and formulaic structures that make writing feel machine-made. This Skill edits drafts, docs, and PR bodies to remove those patterns while preserving the author's original meaning. ## Core Features & Use Cases - Pattern Detection and Rewrite: Scans text against a 31-pattern catalog covering content, language, style, filler, and jargon, then rewrites each hit without changing the claims. - Voice Restoration: Applies voice rules such as varied sentence rhythm, first person where it fits, and concrete specifics so the result does not read as sterile. - Self-Audit Pass: Runs a final check asking what still makes the text obviously AI generated and fixes remaining tells. - Use Case: Paste an AI-drafted PR description or blog post and receive a version with plain words, active voice, and natural rhythm that reads as human-written. ## Quick Start Use the unslop skill to rewrite this draft and remove the AI writing patterns while keeping my meaning intact.

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 skill on the draft text. It scans against a 31-pattern catalog, rewrites each hit, applies voice rules for rhythm and specificity, then self-audits for remaining tells while preserving your original meaning.

What AI writing tells does this skill detect?▼

It detects puffery, vague attributions, AI vocabulary like delve and pivotal, em dash and colon overuse, chatbot phrases, excessive hedging, filler phrases, and abstract jargon nouns such as substrate or paradigm.

Does rewriting AI text change the original meaning?▼

No. The skill edits wording only and never alters claims. It explicitly avoids adding new facts, praise, or hedges during the rewrite, so the author's intent stays intact.

Can I use this on PR descriptions and documentation?▼

Yes. The skill works on any prose surface including drafts, docs, and PR bodies. It is invoked explicitly by the user rather than automatically, since model invocation is disabled.

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

Removing patterns alone leaves sterile, voiceless writing. The skill's third step adds voice through varied sentence rhythm, opinions, first person where fitting, and concrete specifics instead of generic statements.