humanize

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

Updated Sep 8, 2026
One-click install
npx skills add https://github.com/salomepoulain/makery-stations --skill humanize-salomepoulain
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: humanize
Source: https://github.com/salomepoulain/makery-stations/tree/main/stations/claude/workbench/pantry/skills/humanize
Command: npx skills add https://github.com/salomepoulain/makery-stations --skill humanize-salomepoulain

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated text carries recognizable patterns like not-X-but-Y contrasts, one-line closers, forced triads, and inflated claims that make prose sound robotic. This Skill rewrites such text so it reads like natural human writing without changing what it says. ## Core Features & Use Cases - Pattern Detection and Removal: Identifies and fixes 25 documented AI writing tells across staging, rhythm, inflation, formatting, and chatbot residue, based on Wikipedia's "Signs of AI writing." - Voice Matching: Adapts rewrites to a provided writing sample, matching sentence length, word choice, and punctuation habits. - Fact Preservation: Keeps every supported claim, name, number, and citation while removing only stylistic tells; never invents facts. - Use Case: Paste an AI-drafted blog post and receive a rewrite that removes dashes, triads, and sales language while keeping all the original information intact. ## Quick Start Rewrite this AI-generated draft so it reads like natural human writing while keeping all the facts unchanged.

Frequently Asked Questions about humanize

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 inflated claims, then rewrite each flagged sentence to state its point directly. This Skill automates that process using 25 documented patterns from Wikipedia's Signs of AI writing.

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," and chatbot residue like "I hope this helps." Weaker signals include excessive em dashes, forced triads, bold labels on every list item, and stock AI vocabulary like "delve" or "tapestry."

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 stylistic patterns and never adds facts that are not in the original text or provided by the user.

Can the rewrite match my personal writing style?

Yes. Provide a writing sample and the rewrite will match its sentence length, word choice, punctuation, openings, and transitions. The sample overrides default rules, so if you use dashes regularly, they are kept at a similar rate.

When should AI writing patterns be left alone?

Leave watched phrases inside quotations, titles, proper names, or passages discussing the phrase itself. Text written before November 2022 is not AI-written, and weak tells like a single dash or curly quotes need company from other patterns before editing.