Xiaohongshu Deep Research

Deep research on Xiaohongshu (小红书) topics. Use when user wants to research a topic, analyze trends, gather insights from top posts, or produce a summary repo...

Security Scan

The skill's instructions, required artifacts, and behavior are coherent with its stated purpose (researching Xiaohongshu via a local proxy service), but it depends on an external local service (xiaohongshu-mcp) which you should verify before use.

Purpose & Capability

Name and description match the instructions: the skill performs keyword expansion, searches via an API, sorts by engagement, and writes a report. The declared requirement (xiaohongshu-mcp running and a logged-in Xiaohongshu account) is consistent with the stated functionality.

Instruction Scope

SKILL.md instructs the agent to call local API endpoints (http://localhost:18060), create directories under the user's home (~/xiaohongshu-research/...), save raw JSON, and process it with jq. It does not instruct reading unrelated system files or exfiltrating data to remote endpoints. Note: the skill relies on the external local service to access your Xiaohongshu account/session — that service, not the skill text, could access cookies or network resources.

Install Mechanism

Instruction-only skill with no install spec and no code files. Nothing is downloaded or written by the skill itself.

Credentials

The skill requests no environment variables or credentials itself. It does require a logged-in Xiaohongshu account and a running xiaohongshu-mcp service (local proxy) which is a reasonable, proportional dependency for the described task.

Persistence & Privilege

always:false and user-invocable:true (normal). The skill does not request permanent platform presence or claim to modify other skills or system-wide configs. It will write output files under the user's home directory as documented.

Assessment

This skill is internally consistent, but before installing or running it: 1) Verify the xiaohongshu-mcp service is from a trusted source (the SKILL.md references xpzouying/xiaohongshu-mcp) — inspect that project's code and deployment instructions. 2) Understand the local proxy will use your logged-in Xiaohongshu session (cookies/tokens) — run it in a trusted or isolated environment if you have concerns. 3) Expect the skill to create files under ~/xiaohongshu-research/... and to only use search-result metadata (post bodies and comments are not available). 4) If you don't control or trust the local service, do not provide account credentials or start it on a machine with sensitive sessions. If you want higher assurance, request the upstream repo and verify network activity and storage behavior of xiaohongshu-mcp before proceeding.

小红书话题研究，自动爬取 + 分析 + 输出报告。

前置条件

• xiaohongshu-mcp 服务运行中 (http://localhost:18060/mcp)
• 已登录小红书账号

存储位置

~/xiaohongshu-research/{keyword}_{YYYYMMDD_HHmm}/
├── raw/posts.json        # 原始数据
├── analysis/summary.md   # 完整报告
└── metadata.json         # 研究配置

研究流程

1. 关键词扩展 — 主词 + 3-4 个相关词
2. 批量搜索 — POST /api/v1/feeds/search
3. 去重排序 — 按点赞数取 Top 20-50
4. 生成报告 — 含链接、可转发摘要

帖子链接格式

https://www.xiaohongshu.com/explore/{note_id}

报告结构

# {主题} 小红书研究

---

## 📱 速览（可直接转发）

{2-3段自然语言总结，像朋友分享一样写}

值得看的几篇：
• {标题} — {链接}
• {标题} — {链接}

---

## 数据概览

采集 {N} 篇帖子，共 {likes} 赞 / {collects} 收藏

## Top 10

1. **{标题}** @{作者}
   {likes}👍 {collects}📁 | [查看]({link})

## 发现

{自然语言描述趋势和洞察}

## 数据

原始数据: `{path}`

写作风格

• 速览部分：像给朋友发消息，口语化，有观点
• 正文部分：简洁，重点突出，避免套话
• 不要用"本报告"、"经过分析"这类官腔

限制

⚠️ API 限制：帖子详情和评论无法获取，报告基于搜索结果元数据生成。

详细工作流

见 references/workflow.md

Credits

基于 xpzouying/xiaohongshu-mcp