Baoyu Image Cards

Breaks down articles, guides, or social content into 1-10 illustrated cards optimized for WeChat and Xiaohongshu. You get 12 visual styles (cute, minimal, notion, chalkboard), 8 layouts (dense, sequential, grid), and 3 color palettes that override the defaults. It writes each prompt to disk first, then batches generation through whatever image backend you have available, whether that's Codex imagegen or something else. Confirmation is on by default unless you pass --yes. The skill auto-detects Chinese keywords like "小红书图片" or "微信图文" but also responds to plain "image cards". Useful when you need carousel content that actually renders as images instead of just getting SVG fallbacks.

Install to Claude Code

npx -y skills add jimliu/baoyu-skills --skill baoyu-image-cards --agent claude-code