# Send 小红书skill to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "xiaohongshu-skill",
    "name": "小红书skill",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/DeliciousBuding/xiaohongshu-skill",
    "canonicalUrl": "https://clawhub.ai/DeliciousBuding/xiaohongshu-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/xiaohongshu-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=xiaohongshu-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "requirements.txt",
      "SKILL.md",
      "scripts/client.py",
      "scripts/comment.py",
      "scripts/explore.py",
      "scripts/feed.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/xiaohongshu-skill"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/xiaohongshu-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/xiaohongshu-skill",
    "agentUrl": "https://openagent3.xyz/skills/xiaohongshu-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/xiaohongshu-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/xiaohongshu-skill/agent.md"
  }
}
```
## Documentation

### 小红书 Skill

基于 Python Playwright 的小红书（rednote）交互工具，通过浏览器自动化从 window.__INITIAL_STATE__（Vue SSR 状态）中提取结构化数据。

### 前置条件

在 {baseDir} 目录下安装依赖：

cd {baseDir}
pip install -r requirements.txt
playwright install chromium

Linux/WSL 环境还需运行：

playwright install-deps chromium

### 快速开始

所有命令从 {baseDir} 目录运行。

### 1. 登录（首次必须）

cd {baseDir}

# 打开浏览器窗口，显示二维码供微信/小红书扫描
python -m scripts qrcode --headless=false

# 检查登录是否仍然有效
python -m scripts check-login

在无头环境下，二维码图片保存到 {baseDir}/data/qrcode.png，可通过其他渠道发送扫码。

### 2. 搜索

cd {baseDir}

# 基础搜索
python -m scripts search "关键词"

# 带筛选条件
python -m scripts search "美食" --sort-by=最新 --note-type=图文 --limit=10

筛选选项：

--sort-by：综合、最新、最多点赞、最多评论、最多收藏
--note-type：不限、视频、图文
--publish-time：不限、一天内、一周内、半年内
--search-scope：不限、已看过、未看过、已关注
--location：不限、同城、附近

### 3. 帖子详情

cd {baseDir}

# 使用搜索结果中的 id 和 xsec_token
python -m scripts feed <feed_id> <xsec_token>

# 加载评论
python -m scripts feed <feed_id> <xsec_token> --load-comments --max-comments=20

### 4. 用户主页

cd {baseDir}
python -m scripts user <user_id> [xsec_token]

### 数据提取路径

数据类型JavaScript 路径搜索结果window.__INITIAL_STATE__.search.feeds帖子详情window.__INITIAL_STATE__.note.noteDetailMap用户信息window.__INITIAL_STATE__.user.userPageData用户笔记window.__INITIAL_STATE__.user.notes

Vue Ref 处理： 始终通过 .value 或 ._value 解包：

const data = obj.value !== undefined ? obj.value : obj._value;

### 反爬保护

本 Skill 内置了针对小红书反机器人策略的保护措施：

频率控制：两次导航间自动延迟 3-6 秒，每 5 次连续请求后冷却 10 秒
验证码检测：自动检测安全验证页面重定向，触发时抛出 CaptchaError 并给出处理建议
仿人类行为：随机延迟、滚动模式、User-Agent 伪装

触发验证码时的处理：

等待几分钟后重试
运行 cd {baseDir} && python -m scripts qrcode --headless=false 手动通过验证
如 Cookie 失效，重新扫码登录

### 输出格式

所有命令输出 JSON 到标准输出。搜索结果示例：

{
  "id": "abc123",
  "xsec_token": "ABxyz...",
  "title": "帖子标题",
  "type": "normal",
  "user": "用户名",
  "user_id": "user123",
  "liked_count": "1234",
  "collected_count": "567",
  "comment_count": "89"
}

### 文件结构

{baseDir}/
├── SKILL.md              # 本文件（Skill 规范）
├── README.md             # 项目文档
├── requirements.txt      # Python 依赖
├── LICENSE               # MIT 许可证
├── data/                 # 运行时数据（二维码、调试输出）
└── scripts/              # 核心模块
    ├── __init__.py
    ├── __main__.py       # CLI 入口
    ├── client.py         # 浏览器客户端封装（频率控制 + 验证码检测）
    ├── login.py          # 二维码扫码登录流程
    ├── search.py         # 搜索（支持多种筛选）
    ├── feed.py           # 帖子详情提取
    └── user.py           # 用户主页提取

### 跨平台兼容性

环境无头模式有头模式（扫码登录）备注Windows支持支持主要开发环境WSL2 (Win11)支持通过 WSLg 支持需要 playwright install-depsLinux 服务器支持不适用二维码保存为图片文件

### 注意事项

Cookie 过期：Cookie 会定期过期，check-login 返回 false 时需重新登录
频率限制：过度抓取会触发验证码，请依赖内置的频率控制
xsec_token：Token 与会话绑定，始终使用搜索/用户结果中的最新 Token
仅供学习：请遵守小红书的使用条款，本工具仅用于学习研究
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: DeliciousBuding
- Version: 1.0.2
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-04-30T16:55:25.780Z
- Expires at: 2026-05-07T16:55:25.780Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/xiaohongshu-skill)
- [Send to Agent page](https://openagent3.xyz/skills/xiaohongshu-skill/agent)
- [JSON manifest](https://openagent3.xyz/skills/xiaohongshu-skill/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/xiaohongshu-skill/agent.md)
- [Download page](https://openagent3.xyz/downloads/xiaohongshu-skill)