humanizer

Detect and rewrite AI-generated writing patterns to produce natural human-sounding prose.

Updated Aug 1, 2026
One-click install
npx skills add https://github.com/siegenthalerroger/.llmctl-marketplace --skill humanizer-siegenthalerroger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/siegenthalerroger/.llmctl-marketplace/tree/main/plugins/llmctl-core-0.4.0/skills/humanizer
Command: npx skills add https://github.com/siegenthalerroger/.llmctl-marketplace --skill humanizer-siegenthalerroger

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? AI-generated text carries recognizable tells such as em dash overuse, rule-of-three lists, promotional language, and vague attributions that make writing sound robotic. This Skill identifies those patterns and rewrites the text so it reads as natural human prose while preserving every fact from the source. ## Core Features & Use Cases - Pattern Detection and Removal: Scans for 33 documented AI writing patterns drawn from Wikipedia's "Signs of AI writing" guide, covering content, language, style, and communication tells. - Fact-Preserving Rewrites: Rewrites text without inventing facts, names, dates, or citations, and supports voice calibration from a user-provided writing sample. - Use Case: Paste a blog draft that reads like chatbot output, and receive a draft rewrite, a brief audit of remaining AI tells, and a final version with no em dashes, filler phrases, or formulaic structures. ## Quick Start Use the humanizer skill to rewrite this text so it sounds natural and human-written while keeping all the original facts.

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?▼

Run the text through a rewrite pass that targets known AI tells: em dashes, rule-of-three lists, promotional adjectives, vague attributions, and filler phrases. This Skill detects 33 such patterns and rewrites the prose while preserving every original fact.

What are the signs of AI-generated writing?▼

Common signs include inflated significance language, superficial -ing phrase analyses, copula avoidance, negative parallelisms, excessive hedging, and formulaic conclusions. The patterns here are based on Wikipedia's "Signs of AI writing" guide maintained by WikiProject AI Cleanup.

Can the rewrite match my own writing style?▼

Yes. Provide a sample of your previous writing and the Skill analyzes its sentence lengths, vocabulary, punctuation, and recurring phrases, then matches those habits. A sample even overrides default rules like the em dash ban.

Does humanizing text change the facts or meaning?▼

No. The rewrite must not add any fact, name, number, date, quote, or citation that is not in the source text. The audit step explicitly checks for fabricated details before delivering the final version.

When should I not remove AI writing patterns?▼

Avoid over-editing when text shows human signals like specific unusual details, mixed feelings, dated references, or varied sentence rhythm. Isolated tells such as a single em dash or curly quotes from a word processor are not reliable AI indicators.