Baoyu Image Cards

jimliu/baoyu-skills

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.

installs

6.2K

GitHub stars

27K

last updated

Aug 21, 2026

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.