Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Red book content creation

v1.0.1

将文章、技术文档等内容转换为适合小红书发布的 HTML 格式,生成封面图和内容截图,配好标题和正文摘要。 用户提供原始内容(Markdown 或纯文本)后,AI 生成适配小红书风格的多图 HTML 页面,并调用截图工具生成可直接发布的图片。 适用于:技术博客分享、知识干货、產品介绍、营销内容等。

1· 103·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for wenhulove333/red-book-content-creation.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Red book content creation" (wenhulove333/red-book-content-creation) from ClawHub.
Skill page: https://clawhub.ai/wenhulove333/red-book-content-creation
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install red-book-content-creation

ClawHub CLI

Package manager switcher

npx clawhub@latest install red-book-content-creation
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description, HTML templates, and the two scripts all align with producing styled HTML and screenshots for 小红书 posts. There are no unexpected credentials, remote endpoints, or binaries requested that would be incoherent with the stated purpose.
Instruction Scope
SKILL.md and scripts stay within content generation and local screenshotting. Minor issues: the README examples reference an absolute /root/.openclaw path (example-only), and generate_content.sh replaces several placeholders (SUBTITLE, TAGS) even though those variables are not defined in the script—this is an implementation bug rather than malicious behavior. The scripts only read user-provided content and write outputs in the skill directory; they do not access other system files or environment secrets.
Install Mechanism
There is no install spec and no external downloads. The tool relies on local binaries (wkhtmltoimage) and Python libraries (imgkit); requiring those is reasonable for HTML→image conversion. No network fetches or obscure install sources are present in the repository.
Credentials
The skill requests no environment variables or credentials. The only external requirements are typical system tools (wkhtmltoimage, ImageMagick, Python3) that are proportionate to rendering and screenshotting HTML.
Persistence & Privilege
always:false and user-invocable defaults are used. The skill writes outputs into its own outputs/ directory; it does not modify other skills or system-wide configuration. It does not request privileged or persistent presence.
Assessment
This skill appears to do what it says: generate styled HTML and create screenshots locally. Before installing/running: 1) ensure wkhtmltoimage and the Python imgkit dependency are installed and available on PATH (the tool depends on them); 2) review and test the scripts in a safe, writable workspace—generate_content.sh uses sed -i to replace placeholders and references unset variables (SUBTITLE, TAGS) which may yield empty fields or break on some systems (BSD sed vs GNU sed differences); 3) note the SKILL.md examples use an absolute /root path—adjust to your environment; 4) the screenshot script uses a fixed estimated content height and will create multiple chunk images—check outputs for completeness; 5) the skill runs locally and does not exfiltrate data, but avoid feeding it sensitive secrets since it will create files in the skill workspace. If you need further assurance, run the scripts on non-sensitive sample content and confirm behavior before using with real posts.

Like a lobster shell, security has layers — review code before you run it.

latestvk976jj8w2qa552j5ftcb7ehv5185mm03
103downloads
1stars
2versions
Updated 1d ago
v1.0.1
MIT-0

小红书内容生成技能

功能概述

将任意文章/内容转换为小红书风格的 HTML 页面,输出多张可截图发布的图片,并附上标题 + 正文摘要

支持两种风格

  • 🎨 热情风(红色系):#FF6B6B → #FF8E53 橙红渐变,适合激情、励志、营销类内容
  • 🔬 科技风(蓝紫系):#4A90E2 → #7B68EE 蓝紫渐变,适合技术干货、科普、编程类内容

风格选择

风格主色调渐变适用场景
热情风#FF6B6B (珊瑚红)#FF6B6B → #FF8E53营销/励志/个人成长/情感类
科技风#4A90E2 (科技蓝)#4A90E2 → #7B68EE技术干货/编程/数据库/架构类

生成内容时,根据内容主题自动选择风格:

  • 数据库、缓存、架构、编程 → 科技风
  • 营销、增长、个人IP、情感 → 热情风
  • 可通过指令指定风格,如"用热情风生成"

使用方式

方式一:发送内容给 AI

直接把你的文章内容发给我(可以是 Markdown 或纯文本),告诉我"帮我生成小红书内容"或"做成适合小红书的格式"。

示例:

"帮我把这篇关于 Redis 缓存的文章做成小红书风格的内容"

我会自动:

  1. 分析内容结构,提取核心要点
  2. 根据内容类型选择合适风格(科技风/热情风)
  3. 生成适配小红书的 HTML 页面(封面 + 多个内容区块)
  4. 截图并发送给你
  5. 提供标题和正文建议

方式二:命令行调用

cd ~/.openclaw/workspace/skills/xiaohongshu-content
bash scripts/generate_content.sh "你的内容" "输出标题" [tech|passion]

输出规格

项目说明
图片数量1张完整长图(包含所有内容)
图片格式PNG
图片宽度680px(小红书标准宽度)
图片高度自动(根据内容长度)
HTML输出可在浏览器打开查看完整效果
截图工具wkhtmltoimage

HTML 模板

技能包含两个预设模板:

科技风 (tech_style.html)

  • 主色: #4A90E2 (科技蓝)
  • 渐变: #4A90E2 → #7B68EE (蓝紫渐变)
  • 背景: #F0F4FF / #F8F0FF (淡蓝/淡紫)
  • 强调色: #4A90E2 (蓝), #7B68EE (紫)
  • 适用: 技术干货、编程、数据库、架构、DevOps 等

热情风 (passion_style.html)

  • 主色: #FF6B6B (珊瑚红)
  • 渐变: #FF6B6B → #FF8E53 (橙红渐变)
  • 背景: #FFF5F5 / #FFF9F0 (淡粉/淡黄)
  • 强调色: #FF6B6B (红), #FF8E53 (橙)
  • 适用: 营销、个人成长、情感、励志等

通用组件

两种风格共用相同的组件结构:

  • 封面卡片:emoji + 标题 + 副标题 + 标签
  • 内容卡片:图标 + 标题 + 副标题 + 要点列表 + 类比框
  • 对比表格:渐变色表头 + 斑马纹行
  • 流程图:渐变按钮 + 箭头
  • 徽章标签:圆角胶囊样式
  • 总结网格:2列 Summary Card

截图脚本用法

cd /root/.openclaw/workspace/skills/xiaohongshu-content/outputs

# 生成长图(完整内容)
wkhtmltoimage --width 680 --quality 90 input.html output.png

# Python 截图(可获取精确尺寸)
python3 scripts/take_screenshot.py --input input.html --output output.png --width 680

标题与摘要生成规则

标题公式

[符号] + [核心关键词] + [效果词] + [平台词]

示例(科技风):
🔍 一文搞懂MySQL索引核心原理
💡 5分钟理解Redis缓存雪崩
🚀 微服务架构避坑指南

示例(热情风):
🔥 这个思维模式,悄悄拉开了差距
✨ 3个技巧,让你的效率翻倍
💪 坚持30天,发生惊人变化

摘要公式

[一句话概括价值] + [时间/难度暗示] + [行动引导]

示例:
Redis缓存穿透、击穿、雪崩一篇全搞懂,收藏慢慢看~
#Redis #缓存技术 #后端开发 #知识分享

标签策略

  • 3-5个标签
  • 结构:1个领域词 + 1-2个技术词 + 1个平台词 + 1个情绪词
  • 示例:#MySQL #数据库索引 #技术干货 #知识分享

依赖项

依赖用途安装
Python3截图脚本系统自带
wkhtmltoimageHTML渲染引擎apt install wkhtmltopdf
ImageMagick图片裁剪apt install imagemagick

文件结构

xiaohongshu-content/
├── SKILL.md                    # 本技能说明
├── scripts/
│   ├── generate_content.sh     # 内容生成主脚本
│   ├── take_screenshot.py      # Python截图工具
│   └── open_preview.sh         # 浏览器打开预览
├── templates/
│   ├── tech_style.html         # 科技风模板(蓝紫渐变)
│   └── passion_style.html      # 热情风模板(红橙渐变)
└── outputs/                    # 生成的内容目录

示例输出

用户提供内容 → AI 生成以下内容:

标题: 🔍 MySQL 索引全景图解|用图书馆类比秒懂索引底层逻辑

正文:

聚簇索引、非聚簇索引、ICP、MRR、GROUP BY、最左前缀 —— 这篇用"图书馆"类比帮你彻底搞懂! 收藏慢慢看 💪 #MySQL #数据库索引 #技术干货 #知识分享 #后端开发

图片: 1 张完整长图(可发布到小红书)


注意事项

  1. 图片宽度固定 680px,适配小红书笔记宽度
  2. 长图高度根据内容自动增长,完整包含所有信息
  3. 标签使用 emoji + 文字,增加视觉吸引力
  4. 摘要控制在 100 字以内,小红书显示完整
  5. 标题控制在 20 字以内,超过会被截断
  6. 风格默认选择:技术类 → 科技风,营销/个人类 → 热情风

Comments

Loading comments...