What problem does it solve? AI-generated text contains recognizable patterns—inflated significance claims, promotional language, em dash overuse, rule-of-three structures, and chatbot artifacts—that make writing sound robotic and erode reader trust. This Skill identifies and removes those tells while preserving meaning and injecting genuine voice. ## Core Features & Use Cases - Pattern Detection: Scans text for 24 documented AI writing patterns based on Wikipedia's "Signs of AI writing" guide, including vague attributions, superficial -ing phrases, negative parallelisms, and filler hedging. - Guided Rewriting: Replaces AI-isms with natural alternatives using concrete before/after examples for each pattern category. - Voice Injection: Goes beyond cleanup to add personality—varied sentence rhythm, first-person perspective, opinions, and specific details. - Self-Audit Loop: Runs a final two-pass check ("What makes this obviously AI generated?" then "Make it not obviously AI generated") to catch remaining tells. - Use Case: Paste an AI-drafted blog post, marketing email, or documentation page and receive a draft rewrite, a brief audit of remaining AI tells, and a final humanized version. ## Quick Start Ask the AI to humanize a piece of text, for example: "Humanize this AI-drafted product announcement and remove anything that sounds machine-generated."