Takes your markdown or HTML content and turns it into sequential 3:4 screenshots ready for Xiaohongshu posts. The workflow is pretty thorough: it generates an AI cover image using the baoyu-cover-image skill, wraps everything in a styled HTML page with proper Chinese typography, then captures screenshots that don't cut text mid-sentence. Handles multi-account setups with folder routing based on explicit flags, path inference, or template mappings. The compliance checking is notable here, it validates both image concepts and text content against Xiaohongshu's community guidelines before generating anything. If you're publishing to Little Red Book regularly and tired of manual formatting, this automates the annoying parts.

skills.sh installs
2K
GitHub stars
7
last updated
Aug 21, 2026

Install

$ npx -y skills add iamzifei/xiaohongshu-images-skill --skill xiaohongshu-images --agent claude-code

Installs into .claude/skills of the current project.

Files

Xiaohongshu Images Skill

This skill transforms markdown, HTML, or text content into beautifully styled HTML pages with AI-generated cover images, then captures them as sequential screenshots at 3:4 ratio for Xiaohongshu posting.

Overview

The skill performs the following workflow:

  1. Accept Content: Receives markdown, HTML, or txt format content from the user
  2. Load Prompt Template: Reads the prompt template from prompts/default.md in this skill's directory
  3. Determine Output Account: Determines which account folder to use (see Account Folder Resolution below)
  4. Generate Cover Image: Uses /baoyu-cover-image skill to generate a cover image based on the article content
  5. Generate HTML: Creates a beautifully styled HTML page following the prompt template specifications
  6. Save Output: Saves the HTML to ~/Dev/obsidian/{account_folder}/articles/<date-title>/xhs-preview.html
  7. Capture Screenshots: Takes sequential 3:4 ratio screenshots of the entire page without cutting text

Account Folder Resolution

The skill determines the output account folder using the following priority:

Priority 1: Explicit --account Parameter

Sponsors

Details

Repository
github.com/iamzifei/xiaohongshu-images-skill
Category
Frontend Development
1cognitedata avatarcode-qualitycognitedata/builder-skillsMUST be used whenever reviewing a Flows app for code quality, maintainability, or clean code issues — before a PR review, after a feature is complete, or when t2Kskills.sh installs
2enzed avatarr3f-physicsenzed/r3f-skillsReact Three Fiber physics with Rapier - RigidBody, colliders, forces, joints, sensors. Use when adding physics simulation, collision detection, character contro2Kskills.sh installs
3nvidia avatardynamo-troubleshootnvidia/skillsDiagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use 1.9Kskills.sh installs
4nexu-io avatarreference-design-contractnexu-io/open-designTurn vague taste, screenshots, URLs, product notes, or "make it feel like this" references into a grounded DESIGN.md plus an implementation handoff. Use it befo1.9Kskills.sh installs
5jimmylv avatarbibijimmylv/bibigpt-skillAI video & audio summarizer + repackager. Summarize YouTube, Bilibili, podcasts, TikTok, Twitter/X, Xiaohongshu, and any online video or audio, then optionally 1.9Kskills.sh installs
6cognitedata avatarintegrate-todo-listcognitedata/builder-skillsMUST be used whenever adding a task/todo list feature to a Flows app with Atlas chat. Do NOT manually create todo state management or tool definitions — this sk1.9Kskills.sh installs