What problem does it solve? AI-generated text carries recognizable fingerprints—exaggerated significance, promotional language, em-dash overuse, rule-of-three structures, and chatbot artifacts—that make content feel robotic and untrustworthy. This Skill identifies 24 documented AI writing patterns and rewrites the text so it reads naturally while preserving the original meaning and tone. ## Core Features & Use Cases - 24-pattern detection: Scans for content, language, style, and communication patterns documented in Wikipedia's "Signs of AI writing" guide, each with before/after examples. - Personality injection: Goes beyond removing bad patterns by adding genuine voice—varied sentence rhythm, first-person perspective, and acknowledged complexity. - Two-pass audit workflow: Produces a draft rewrite, then runs a final "why is this obviously AI-generated" check followed by a second revision to catch residual AI habits. - Use Case: Paste an AI-drafted blog post or report and receive a humanized version with a summary of every change made, from removed filler phrases to fixed vague attributions. ## Quick Start Ask the assistant to humanize a piece of text by pasting it with a request like "人性化这段文本" followed by your content.
