← Back to Skills Marketplace
818
Downloads
1
Stars
1
Active Installs
16
Versions
Install in OpenClaw
/install auto-redbook-content
Description
小红书热点抓取与去AI味改写工具。抓取首页热点→生成去AI味改写提示词→本地存储。
README (SKILL.md)
auto-redbook-content Skill
小红书热点抓取与去 AI 味改写工具。
核心功能
抓取小红书首页热点 → 生成去 AI 味改写提示词 → 本地 JSON 存储
触发方式
抓取 3 条小红书笔记
工作流程
- 抓取热点：通过 xiaohongshu MCP 获取首页热门笔记
- 生成提示词：构建去 AI 味的改写提示词
- 本地存储：输出到
output/xiaohongshu_YYYYMMDD_HHMMSS.json
环境变量
| 变量 | 说明 | 默认值 |
|---|---|---|
| XHS_MAX_RESULTS | 抓取数量 | 3 |
通过环境变量设置，无需 .env 文件。
去 AI 味改写要点
提示词包含以下要求：
- 像真人聊天，不像写作文
- 多用口语化表达
- 打破工整结构
- 加入真实细节
- 避免 AI 常用连接词
输出格式
JSON 文件包含：
- 原始标题、内容、作者
- 去 AI 味改写提示词
- 元数据
依赖
- Node.js >= 14.0.0
- xiaohongshu MCP（可选）
安全说明
脚本本身：
- ✅ 无 shell 执行
- ✅ 无直接网络访问
- ✅ 不读取 .env 文件
- ✅ 仅读取必要环境变量
- ✅ 仅写入 output 目录
在 OpenClaw agent 环境中：
- ⚠️ 可能通过 xiaohongshu MCP 工具进行网络抓取
- ⚠️ MCP 工具由 OpenClaw 环境提供和管理
- ⚠️ 网络访问由 MCP 执行，非脚本直接调用
版本历史
v2.5.2 (2026-03-15)
- 📝 澄清安全说明：区分脚本本身和 agent 环境
v2.5.1 (2026-03-15)
- 🔧 删除 package-lock.json 和 node_modules
- 📝 移除 npm install 说明
v2.5.0 (2026-03-15)
- ✨ 改写提示词增加去 AI 味要求
- 🔒 移除 .env 文件读取
- 🔒 移除 dotenv 依赖
- 🔒 仅读取必要环境变量
Usage Guidance
This skill appears internally consistent and does not request secrets. Before installing/running, confirm the following: (1) The OpenClaw agent/tool 'xiaohongshu MCP' is trusted — if invoked, it will perform network requests and could send fetched content externally; (2) If you or the agent will send the generated prompts or original content to external LLMs or services, be aware that those prompts include original note content and could leak data; (3) Review agent tool permissions and run the skill in a sandbox if you want to avoid any network activity. If you only run the included scripts locally, they generate mock data and only write JSON to the output/ folder.
Capability Analysis
Type: OpenClaw Skill
Name: auto-redbook-content
Version: 2.5.2
The skill bundle is a legitimate tool for fetching Xiaohongshu (Redbook) trends and generating rewrite prompts. The code (scripts/fetch.js, scripts/rewrite.js, scripts/run.js) is transparent, lacks external dependencies, and follows least-privilege principles by restricting file system access to the 'output' directory and delegating network tasks to the host's MCP environment. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Assessment
Purpose & Capability
Name/description (fetch Xiaohongshu hotspots → generate de-AI prompts → save locally) matches the files and package.json. Required binary (node) and permission (fs:write:output) are appropriate and proportionate.
Instruction Scope
SKILL.md and fetch.js state that actual network fetching is performed by an external 'xiaohongshu MCP' tool provided by the OpenClaw agent environment; the included scripts do not perform network I/O and only generate mock data locally. This is coherent, but it means network access would occur only if the agent invokes the MCP tool or another external tool — review the agent/tool behavior before running.
Install Mechanism
No install spec; instruction-only with small JS scripts. Nothing is downloaded or extracted during install; risk from install mechanism is minimal.
Credentials
No required secrets or credentials. One optional env var (XHS_MAX_RESULTS) controls fetch count. package.json declares only fs:write:output. No disproportionate environment or credential requests.
Persistence & Privilege
always is false, agent invocation is normal. The skill only writes to its own output directory and does not modify other skills or system configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install auto-redbook-content - After installation, invoke the skill by name or use
/auto-redbook-content - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.5.2
澄清安全说明：区分脚本本身和agent环境
v2.5.1
删除package-lock和node_modules，确保无外部依赖
v2.5.0
增加去AI味改写要求，移除.env文件读取
v2.4.1
说明真实抓取需要MCP支持
v2.4.0
移除所有外部工具调用和网络访问，极简实现
v2.3.1
增强安全说明文档
v2.3.0
移除飞书集成，纯本地存储，适配单agent独立完成
v2.2.2
修复rewrite.js导出不匹配问题
v2.2.1
清理文档中的AI_API_KEY引用，简化代码，删除过时文档
v2.2.0
移除自动调度功能，明确定位为按需调用工具
v2.1.1
文档优化：明确核心功能（抓取→识别→改写→输出JSON），飞书集成改为可选说明
v2.1.0
安全重构：移除硬编码凭证，改用环境变量；优化错误处理和日志输出
v2.0.0
v2.0.0: 完整重构
v1.1.2
修复元数据不匹配问题：明确声明所有必需环境变量；增加数据流向说明、法律风险提示和外部依赖说明
v1.1.1
🔒 安全修复版本：修复 shell 注入风险、完善配置元数据、增加安全文档
v1.0.0
首次发布：支持小红书笔记抓取、图片识别（Vision+OCR）、AI洗稿、飞书表格写入
Metadata
Frequently Asked Questions
What is Auto Redbook Content?
小红书热点抓取与去AI味改写工具。抓取首页热点→生成去AI味改写提示词→本地存储。 It is an AI Agent Skill for Claude Code / OpenClaw, with 818 downloads so far.
How do I install Auto Redbook Content?
Run "/install auto-redbook-content" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Auto Redbook Content free?
Yes, Auto Redbook Content is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Auto Redbook Content support?
Auto Redbook Content is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Auto Redbook Content?
It is built and maintained by Shaojie66 (@shaojie66); the current version is v2.5.2.
More Skills