humanizer

Overview

A Claude Code skill that identifies and removes signs of AI-generated writing to make text sound more natural and human. Based on Wikipedia's comprehensive "Signs of AI writing" guide maintained by WikiProject AI Cleanup, it detects patterns like inflated symbolism, promotional language, em dash overuse, rule of three, AI vocabulary words, and excessive conjunctive phrases.

Key Features

• Pattern Detection - Scans for specific AI writing patterns including inflated symbolism, superficial -ing analyses, vague attributions, negative parallelisms, and excessive conjunctive phrases
• Personality Injection - Goes beyond removing bad patterns to add actual voice, opinions, humor, varied rhythm, and acknowledgment of complexity
• Voice Preservation - Maintains the intended tone (formal, casual, technical) while replacing AI-isms with natural alternatives
• Soulless Writing Detection - Identifies writing that is technically clean but still obviously AI-generated due to uniform sentence length, lack of opinions, and absence of personality
• Practical Before/After Examples - Provides concrete examples showing how to transform sterile, algorithmically structured text into writing with genuine human character

Who is this for?

This skill is essential for anyone who uses AI to draft text and needs the output to read as genuinely human-written. It is particularly valuable for content creators, writers, marketers, and professionals who want to use AI as a drafting tool while ensuring their published content passes both human scrutiny and AI detection tools.