humanizer

Rewrite text to remove AI writing patterns and restore natural voice.

Updated May 13, 2026
One-click install
npx skills add https://github.com/superfhp/lumi-agent-body --skill humanizer-superfhp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/superfhp/lumi-agent-body/tree/main/skills/creative/humanizer
Command: npx skills add https://github.com/superfhp/lumi-agent-body --skill humanizer-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated text carries recognizable patterns—significance inflation, promotional language, em dash overuse, formulaic structures—that make writing sound robotic and erode reader trust. This Skill identifies 29 documented AI writing tells and rewrites text to sound natural and human. ## Core Features & Use Cases - Pattern Detection and Removal: Scans for 29 AI writing patterns across content, language, style, and communication categories, based on Wikipedia's Signs of AI writing guide. - Voice Calibration: Analyzes a user-provided writing sample and matches its sentence rhythm, word choice, and tone in the rewrite. - Personality Injection: Goes beyond removing bad patterns by adding opinions, varied rhythm, and first-person perspective to avoid sterile output. - Use Case: Paste an AI-drafted blog post and receive a draft rewrite, a brief audit of remaining AI tells, and a final version that reads like a person wrote it. ## Quick Start Humanize this text and remove anything that makes it sound AI-generated: [paste your draft here].

Frequently Asked Questions about humanizer

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

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

Identify common AI writing patterns like significance inflation, promotional language, and formulaic structures, then rewrite those sections with specific details and varied sentence rhythm. This Skill automates that process using 29 documented patterns from Wikipedia's Signs of AI writing guide.

What are the most common signs of AI writing?▼

Common tells include overused words like delve and testament, em dash overuse, rule-of-three groupings, vague attributions like experts argue, superficial -ing phrases, and generic positive conclusions. Chatbot artifacts like I hope this helps are also immediate giveaways.

Can I match my own writing style when humanizing text?▼

Yes, provide a sample of your own writing either inline or as a file path. The Skill analyzes your sentence length, word choice, punctuation habits, and transitions, then matches that voice in the rewrite instead of using a default style.

Does humanizing text work on files or only pasted text?▼

Both work. Paste text directly for an inline rewrite, or point to a file which gets read and edited with targeted patches. For markdown documents in a repository, section-by-section patches are cleaner than full rewrites.

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

Removing flagged words is only half the job. Sterile writing with uniform sentence length, no opinions, and no first-person perspective still reads as machine-made. The rewrite must add varied rhythm, specific feelings, and genuine personality.