humanizer

Rewrite AI-sounding prose to remove detectable AI writing patterns while preserving meaning.

3|Updated Feb 15, 2025
One-click install
npx skills add https://github.com/mark-torres10/ai_tools --skill humanizer-mark-torres10
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/mark-torres10/ai_tools/tree/main/skills/humanizer-writing
Command: npx skills add https://github.com/mark-torres10/ai_tools --skill humanizer-mark-torres10

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated text carries recognizable patterns such as not-X-but-Y contrasts, one-line closers, forced triads, em dashes everywhere, inflated claims, and chatbot residue that make prose sound robotic. This Skill systematically detects and rewrites those patterns so text reads like a person wrote it, without changing what it says. ## Core Features & Use Cases - Pattern Detection and Rewrite: Identifies 25 documented AI writing tells grouped into staging, rhythm, inflation, formatting, and chat leftovers, then rewrites each passage naturally. - Voice Matching: When given a writing sample, matches its sentence length, word choice, punctuation, and transitions so the output sounds like the original writer. - Fact Preservation: Keeps every supported claim, name, number, date, quote, and citation while removing only the AI-sounding dressing; never invents facts. - Use Case: Paste an AI-drafted blog post and receive a marked-up analysis of remaining patterns plus a final rewrite that reads naturally and keeps all original information. ## Quick Start Rewrite this AI-generated draft to remove AI writing patterns while keeping all facts and matching my natural voice.

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 not-X-but-Y contrasts, one-line closers, forced triads, and stock AI vocabulary, then rewrite each passage to state points directly. This Skill automates that process using 25 documented patterns from Wikipedia's Signs of AI writing guide.

What are the most common signs of AI writing?

The strongest tells are not-X-but-Y contrasts, one-line dramatic closers, staged openers like "let's dive in", em dashes used everywhere, forced triads, inflated significance phrases, and chatbot residue like "I hope this helps". Weaker tells include stacked qualifiers and decorative bold labels.

Does rewriting AI text change the facts or meaning?

No. The rewrite keeps every supported claim, name, number, date, quote, and citation from the source. It only removes AI-sounding phrasing and never adds facts that are not in the source or provided by the user.

Can the rewrite match my personal writing style?

Yes. Provide a writing sample and the rewrite matches its sentence length, word choice, punctuation, openings, and transitions. The sample overrides default pattern rules, so habits like frequent dash usage are preserved at the sample's rate.

When should AI writing patterns be left alone?

Patterns inside quotations, titles, proper names, or passages discussing the phrase itself should stay. Text written before November 2022 is not AI-written, and weak tells like a single em dash or curly quotes only justify edits when several tells appear together.