🛍️ 更多精选好物 ›
📊 公开数据一览
| 📦 榜单安装量 | 1.9K |
| ⭐ GitHub Stars | 6 |
| 🗓️ 最近推送 | 2026-02-05 |
| 🌱 项目创建 | 2026-01-14 |
| 💻 语言 / License | Python · 未标注 |
| 🐛 开放Issue | 0 |
📝 工具简介
Claude Skill,根据内容生成3:4比例的小红书图片。
📖 怎么用
先手动复制技能到全局目录,跑 `cp -r xiaohongshu-images-skill ~/.claude/skills/`,开发模式可以用软链 `ln -s /path/to/xiaohongshu-images-skill ~/.claude/skills/xiaohongshu-images-skill`。然后装截图依赖,跑 `pip install playwright` 和 `playwright install chromium`。确认一下 `ls ~/.claude/skills/baoyu-cover-image/SKILL.md` 存在。开始用就在 Claude Code 里输入 `/xiaohongshu-images`,后面直接跟 markdown 内容,比如 `/xiaohongshu-images # 标题 正文内容`,它会自动生成封面和 3:4 截图。
📋 迷你测评
Claude Skill,根据内容生成3:4比例的小红书图片。亮点是比例直接适配平台,省去裁剪。适合小红书内容生产,输出格式固定。
📄 README 要点
这是给Claude Code做小红书图片的技能。它能把markdown、HTML或纯文本内容转成漂亮的HTML页面,配上AI生成的封面图,然后按3:4比例截成一组连续截图,直接就能发小红书。核心功能包括:接受多种格式内容、用/baoyu cover image技能生成编辑风格的封面插图、输出现代排版的HTML页面、智能处理文字边界确保截图不切字。安装需要Python 3.8以上、Claude Code CLI,还要先装好/baoyu cover image技能,然后复制到Claude技能目录并装依赖。特别适合做小红书内容的人,能批量把文字内容变成视觉化图片,省去手动排版。
查看英文原文
Xiaohongshu Images Skill A Claude Code skill that 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. Features Content Processing : Accepts markdown, HTML, or plain text content AI Cover Images : Generates editorial style cover illustrations using /baoyu cover image skill Styled HTML Output : Creates beautifully formatted HTML pages with modern typography Screenshot Capture : Takes sequential 3:4 ratio screenshots optimized for Xiaohongshu Smart Text Boundaries : Ensures no text is cut off in screenshots Installation Prerequisites Python 3.8 or higher Claude Code CLI /baoyu cover image skill installed in /.claude/skills/ Setup 1. Clone or copy this skill to your Claude skills directory: [安装/使用命令见下方] 2. Install Python dependencies: [安装/使用命令见下方] 3. Ensure baoyu cover image skill is installed: [安装/使用命令见下方] Usage Via Claude Code Invoke the skill in Claude Code: [安装/使用命令见下方] Then provide your content: Paste markdown/HTML content directly Provide a file path: /path/to/article.md Provide a URL to fetch content from Example [安装/使用命令见下方] Output The skill generates output in /Dev/obsidian/articles/ / : xhs preview.html Styled HTML preview page attachments/cover xhs.png AI generated cover image attachments/xhs 01.png, xhs 02.png, ... Sequential screenshots Directory Structure [安装/使用命令见下方] Customization Custom Prompt Templates Create custom styling templates in the prompts/ directory: 1. Create a new .md file (e.g., prompts/minimal.md ) 2. Define your HTML/CSS specifications 3. Invoke with: "Use the minimal template for this article" Modifying Styles Edit prompts/default.md to customize: Card dimensions and colors Font families and sizes Typography hierarchy Code block styling Responsive breakpoints Configuration Screenshot Settings Default screenshot dimensions (3:4 ratio for Xiaohongshu): Width: 1080px Height: 1440px Scale factor: 2x (Re
💬 评论(0)
交流使用体验、避坑建议;违规内容将被删除