humanizer

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

Updated Dec 22, 2025
One-click install
npx skills add https://github.com/Endsi3g/prospecting-app --skill humanizer-endsi3g
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/Endsi3g/prospecting-app/tree/main/skills/humanizer_unzipped/humanizer
Command: npx skills add https://github.com/Endsi3g/prospecting-app --skill humanizer-endsi3g

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated text contains recognizable patterns—inflated significance, promotional language, em dash overuse, vague attributions—that make writing sound robotic and untrustworthy. This Skill identifies and removes those tells so edited text reads as naturally human-written. ## Core Features & Use Cases - Pattern Detection: Scans text for 24 documented AI writing patterns based on Wikipedia's "Signs of AI writing" guide, including rule-of-three overuse, negative parallelisms, copula avoidance, and chatbot artifacts. - Guided Rewriting: Replaces AI-isms with natural alternatives while preserving meaning, tone, and voice, and injects personality into sterile text. - Self-Audit Loop: Runs a final anti-AI pass asking "What makes this obviously AI generated?" and revises again before delivering output. - Use Case: Paste an AI-drafted blog post or report and receive a draft rewrite, a list of remaining AI tells, and a final polished version with a summary of changes. ## Quick Start Humanize this AI-generated article draft and remove all signs of machine-written text while keeping my original points intact.

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 inflated significance, rule-of-three lists, and vague attributions, then rewrite those sections with specific details and varied sentence rhythm. This Skill automates that detection and rewriting process using Wikipedia's Signs of AI writing guide.

What are the most common signs of AI-generated writing?

Common signs include words like "delve", "testament", and "landscape", superficial -ing phrases, em dash overuse, negative parallelisms like "not just X but Y", boldface list headers, and chatbot artifacts like "I hope this helps". The Skill checks for 24 documented patterns.

Does humanizing text change its original meaning?

No, the rewriting process explicitly preserves the core message and intended tone, whether formal, casual, or technical. It replaces AI-isms with natural alternatives rather than altering the substance of the content.

Can this detect AI writing in any type of document?

It works on prose content such as articles, essays, blog posts, and reports where AI patterns typically appear. It is less suited to highly structured formats like code, tables, or legal boilerplate where these stylistic signals do not apply.

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 and no opinions still reads as machine-made. The Skill addresses this by adding voice, varied rhythm, first-person perspective, and specific details.