xiaohongshu-publisher

Draft and publish posts to 小红书 (Xiaohongshu/RED). Use when creating content for 小红书, drafting posts, generating cover images, or publishing via browser automation. Covers the full workflow from content creation to browser-based publishing, including cover image generation with Pillow.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "xiaohongshu-publisher" with this command: npx skills add vinplezhang/vinplezhang-xiaohongshu-publisher

小红书 Publisher

Create, format, and publish posts to 小红书 (Xiaohongshu/RED) through browser automation.

Requirements

  • Python 3 with Pillow (pip install Pillow or apt install python3-pil)
  • CJK fontsfonts-noto-cjk on Linux (apt install fonts-noto-cjk), or Noto Sans CJK via Homebrew on macOS
  • OpenClaw browser tool — access to a browser with the user logged into 小红书 creator portal
  • A connected OpenClaw node (or sandbox browser) with Chrome/Chromium for browser automation

Overview

This skill handles the complete 小红书 publishing pipeline:

  1. Draft — Write post content in 小红书 style
  2. Cover — Generate a cover image (1080×1440)
  3. Review — Send draft to user for approval via messaging channel
  4. Publish — Use browser automation to post (or deliver for manual posting)

Workflow

Step 1: Draft Content

Create post content following 小红书 style. See references/content-guide.md for formatting rules, structure, and examples.

Key rules:

  • Title ≤20 chars, with emoji hook
  • Use --- section breaks, emoji bullets, short paragraphs
  • End with question CTA + hashtags (8-12 tags)
  • Save draft to memory/xiaohongshu-draft.md

Step 2: Generate Cover Image

Run the cover generation script:

python3 <skill-dir>/scripts/gen_cover.py --title "主标题" --subtitle "副标题" --tags "标签1,标签2,标签3" --output /path/to/cover.png

Options:

  • --title — Main title (large text, required)
  • --subtitle — Subtitle line (medium text, optional)
  • --tags — Comma-separated feature tags shown as pills (optional)
  • --badge — Top-right badge text (default: "OpenClaw")
  • --output — Output path (default: cover.png)
  • --gradient — Color scheme: purple (default), blue, green, orange, dark

Output: 1080×1440 PNG with gradient background, decorative elements, CJK text.

Step 3: Send for Review

Send the draft content + cover image to the user's messaging channel for review. Format:

📝 小红书草稿 — [主题]

标题:[标题]

[正文内容]

封面图已生成:[path]

请确认:
✅ 可以发布
✏️ 需要修改
❌ 不发

Never auto-publish. Always wait for explicit user approval.

Step 4: Publish via Browser

After user approval, publish using browser automation on the configured node.

See references/browser-publish.md for the complete browser automation steps.

Summary:

  1. Navigate to https://creator.xiaohongshu.com/publish/publish
  2. Enter title and body text
  3. Upload cover image via browser upload action
  4. Click publish

Fallback: Manual Publishing

If browser automation is unavailable (CDP issues, node offline, etc.), send the complete post to the user's channel with all content formatted for easy copy-paste:

📋 小红书发帖内容(请手动发布)

【标题】[标题]

【正文】
[正文内容]

【标签】[hashtags]

封面图:[path to cover image]

Known Limitations

  • Mac Chrome CDP: Chrome launched via SSH/node may fail to bind --remote-debugging-port on macOS (GUI session required). If browser start fails, fall back to manual publishing.
  • Login state: 小红书 creator portal requires login. If the session has expired, ask the user to re-login in their browser before proceeding.
  • Pillow emoji: Pillow cannot render color emoji (NotoColorEmoji.ttf) — use text/icon alternatives in cover images.

Cron Integration

This skill works with cron jobs for scheduled daily posting. Typical cron setup:

Schedule: 0 8 * * * (Asia/Shanghai)
Session: isolated agentTurn
Delivery: announce to user's channel

The cron job message should reference this skill and include the content plan/topic for the day.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Omniscient

全知全能技能 — 整合认知套件、执行框架、系统控制三大能力层,并配备编排引擎。 认知层:四种思维操作码(直用/改进/迁移/构建)覆盖所有思考任务; 执行层:大语言模型 + 命令执行工具,自动化代码生成与脚本执行; 操控层:Windows桌面软件、系统硬件、串口设备、物联网平台、图形界面自动化、蓝牙设备、GPU显卡...

Registry SourceRecently Updated
General

系统清理技能

定期清理OpenClaw系统中的备份、临时及会话文件,分析磁盘使用并检查系统状态,优化系统性能。

Registry SourceRecently Updated
General

Whoislookup

Look up domain WHOIS registration info — registrar, creation date, expiry date, nameservers, and domain status. Use when asked to check who owns a domain, wh...

Registry SourceRecently Updated
General

WayinVideo - Find Moments in the Video

Find specific moments in a video using a natural language query. Ideal for locating particular scenes, topics, or events in long videos (e.g., “the part wher...

Registry SourceRecently Updated