xiaohongshu-images — Claude Code skill: image creation
Turns Markdown, HTML, or text into a styled page and a sequence of 3:4 images for Xiaohongshu. Use it to prepare article content for posting.
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a claude-codeWhat xiaohongshu-images does
Give the skill Markdown, HTML, or plain text. It uses /baoyu-cover-image for a cover, builds an HTML page from prompts/default.md, then captures the page as consecutive 3:4 images. The capture flow is intended to keep text from being cut off.
The output goes into an article folder under ~/Dev/obsidian/. The account folder is chosen from --account, the source file path, or a template mapping. The workflow checks Xiaohongshu requirements for both the cover and page content. The cover step depends on /baoyu-cover-image, so that skill needs to be available for the documented flow to work.
What it helps with
- turn a Markdown article into a styled HTML page
- create a cover for a Xiaohongshu post
- capture a long page as 3:4 images
- save article assets under the selected account folder
Example prompts for the agent
- Create Xiaohongshu images from
article.mdwith/xiaohongshu-images article.md. - Prepare this article for the
james-enaccount:/xiaohongshu-images <article> --account james-en. - Turn
page.htmlinto a sequence of images for Xiaohongshu:/xiaohongshu-images page.html.
How to install xiaohongshu-images
1Skills CLI (Vercel)
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a claude-code2Manually: put the files in place
~/.claude/skills/xiaohongshu-images/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/xiaohongshu-images/
1Skills CLI (Vercel)
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a codex2Manually: put the files in place
.agents/skills/xiaohongshu-images/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a cursor2Manually: put the files in place
.cursor/skills/xiaohongshu-images/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install iamzifei/xiaohongshu-images-skill xiaohongshu-images2Manually: put the files in place
.github/skills/xiaohongshu-images/SKILL.md1Skills CLI (Vercel)
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a gemini-cli2Platform CLI
gemini skills install https://github.com/iamzifei/xiaohongshu-images-skillManually: put the files in place
.devin/skills/xiaohongshu-images/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about xiaohongshu-images
How do I install xiaohongshu-images in Claude Code?
Run npx skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images -a claude-code. The skill file is placed at ~/.claude/skills/xiaohongshu-images/SKILL.md.
What does xiaohongshu-images do?
It creates a cover and a styled HTML page from text, Markdown, or HTML, then captures the page as consecutive 3:4 images for Xiaohongshu.
How does it choose where to save the output?
It checks --account first, then derives the destination from the input file path. If neither identifies an account, it uses the template-to-folder mapping.