domains / families / media / baoyu-xhs-images
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series. Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
The two copies describe the same task but split the procedure in a way that hides real alternatives. JimLiu/baoyu-skills is the canonical, versioned skill and contains the operational constraints the other copy lacks: a strict image-backend resolution order (Codex imagegen, codex CLI, Cursor GenerateImage, other native, then non-native), a hard rule to write each prompt to a standalone file before invoking any backend, a batch-generation policy, and explicit prohibitions against substituting SVG/HTML/canvas for raster output and against programmatically repairing rendered text. LeoYeAI/openclaw-master-skills is a bulk mirror that instead documents the user-facing interface: CLI usage, the 10-style and 8-layout galleries, auto-selection heuristics, three outline strategies, and the session file structure. Neither copy is a complete reproduction of the other; crowning one would either drop the backend/prompt-file/batch constraints or drop the style/layout/outline workflow. The copies also disagree on the number of visual styles (12 in JimLiu vs 10 in LeoYeAI) and on the trigger keywords, so a combined instruction is needed.