What problem does it solve? AI-generated text carries recognizable tells—inflated significance, promotional language, em dash overuse, rule-of-three lists, vague attributions—that make writing sound robotic and erode reader trust. This Skill detects and rewrites those patterns so the text reads like a person wrote it. ## Core Features & Use Cases - 25-pattern detection: Identifies content, language, style, and communication patterns of AI writing, based on Wikipedia's "Signs of AI writing" guide, each with before/after examples. - Two-pass rewrite with audit: Produces a draft rewrite, then runs a "what makes this obviously AI generated" audit and a second revision to catch lingering tells. - Voice restoration: Goes beyond removing bad patterns by adding opinions, varied rhythm, first-person perspective, and specificity so the result has personality rather than sterile neutrality. - Use Case: Paste a ChatGPT-drafted blog post or product announcement and receive a rewritten version stripped of chatbot artifacts, hedging, and formulaic structure, plus a summary of the changes made. ## Quick Start Ask the assistant to humanize a piece of text by pasting it with a request like "humanize this draft so it sounds natural and less AI-generated."