Generates cover images for Xiaohongshu (Little Red Book) posts with a specific design workflow. You get 2-3 design proposals first, pick one, then it produces both an AI-generated version via Gemini and an HTML fallback for comparison. The workflow is opinionated around a creator named Huashu's preferences: warm colors, oversized text that fills the frame, handwritten fonts, paper textures, and absolutely no watermarks. It enforces 3:4 portrait format at 1080x1440px and includes built-in design review scoring before upload. The whole thing assumes you're writing in Chinese and optimizing for mobile feed visibility. If you're posting to Xiaohongshu regularly and want consistent, scroll-stopping visuals without manually designing each one, this handles the full pipeline from concept to image hosting.
npx skills add https://github.com/alchaincyf/huashu-skills --skill huashu-xhs-image