Skip to content
Get packs

Xiaohongshu Image Card Series

Turns content into a set of cartoon-style infographic image cards for social media posts

Source Download skill
Repository
JimLiu/baoyu-skills
Stars
27,191
Licence
MIT
Files
15 files

What it does

Once installed, the agent can take a piece of content and split it into a series of 1-10 infographic-style image cards in a cartoon look, choosing from 12 visual styles, 8 layouts and 3 colour palettes. It asks you to confirm the plan before generating anything, writes a saved prompt for each card, and then asks an image generation tool to render the pictures. It is built mainly for Chinese social platforms such as Xiaohongshu (RED) and WeChat posts.

Great for

  • Creators making multi-image Xiaohongshu or WeChat posts
  • Marketers who want a consistent series of social infographic cards
  • People who already have an image generation backend such as Codex imagegen or Cursor

Skip it if

  • Final print or brand-critical artwork, because generated text on cards can be wrong and the skill forbids fixing it by overlay, so review every card
  • Users without any raster image generation tool, since the skill will stop and ask rather than produce SVG or HTML substitutes
  • Situations needing exact, verified text or data in images, as image models may misspell or alter numbers

Try asking

  • “Turn this article into a 6-card Xiaohongshu 种草 image series in a warm palette”
  • “Make a 小红书图片 carousel summarising these product features with a chalkboard style”
  • “Create WeChat 微信图文 image cards from my meeting notes, 4 cards maximum”
  • “Build image cards with a neon palette for this tutorial, and ask me to confirm the plan first”
Step-by-step guide: how to use Xiaohongshu Image Card SeriesInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    baoyu-xhs-images.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip baoyu-xhs-images.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip baoyu-xhs-images.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Confirm the proposed card plan and style before generation starts, since the skill will not generate without your approval by default
  • Set preferred_image_backend in EXTEND.md to avoid being asked which image tool to use each time
  • Review every rendered card for text errors, and regenerate from a corrected prompt rather than trying to edit the image

What's inside

  • references/codex-imagegen.md
  • references/config/first-time-setup.md
  • references/config/preferences-schema.md
  • references/config/watermark-guide.md
  • references/confirmation.md
  • references/elements/canvas.md
  • references/elements/decorations.md
  • references/elements/image-effects.md
  • references/elements/typography.md
  • references/palettes/macaron.md
  • references/palettes/neon.md
  • references/palettes/warm.md
  • references/presets/bold.md
  • references/presets/chalkboard.md
  • SKILL.md

Redistributed unmodified from JimLiu/baoyu-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.