visual-design-system-extractor

Use when the user asks to analyze reference images, screenshots, moodboards, style frames, brand boards, cinematic stills, or product UI shots to infer a production-grade design system, design tokens, brand/art direction, cinematic language, worldbuilding, motion rules, or YAML style specification. Handles multimodal visual extraction into valid YAML for UI/UX, brand, motion, creative direction, AI generation, and design-engineering workflows. Not for generating images or ordinary frontend implementation unless visual references must be reverse-engineered first.