What problem does it solve? Japanese text written by AI often carries detectable habits—stock phrases, translationese, monotonous rhythm, uniform paragraph structure—that make documents read as machine-generated. This Skill finds those patterns mechanically and guides a structured rewrite so business documents read naturally. ## Core Features & Use Cases - Deterministic lint detection: scripts/lint.py flags forbidden phrases, translationese, antithesis repetition, sentence-length uniformity, lexical diversity, and low specificity, with genre profiles for essay, tech, and business writing. - Structured writing workflow: A four-phase process (design, write, inspect, converge) with quick and full modes, covering minutes, reports, guides, memos, slide outlines, blog posts, and essays. - Diagnosis-only scoring: The score mode returns a 0-100 naturalness score with reasons and fix priorities without rewriting the document. - Use Case: Paste a meeting-minutes draft and ask for a naturalness check; the Skill runs lint, reviews structure and readability, and iterates revisions until no new findings appear. ## Quick Start Ask the AI to rewrite the attached Japanese report so it reads naturally and does not sound AI-generated, using quick mode.
