← Back to Skills Marketplace
xhs-research
by
kunhai1994
· GitHub ↗
· v1.0.0
· MIT-0
96
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xhs-research
Description
小红书调研工具 — 搜索小红书笔记，AI 合成调研报告。
Usage Guidance
This skill appears to do what it says: it runs a local MCP service, asks you to scan a Xiaohongshu QR code, and uses downloaded binaries to perform searches and produce reports. Before installing:
- Inspect and verify the upstream GitHub project (xpzouying/xiaohongshu-mcp) and its releases; malicious actors can publish binaries to a release asset.
- If you don't trust those binaries, don't run setup.py; you can audit source or build binaries yourself.
- Be aware the skill saves login cookies (~/.local/share/xhs-research/cookies.json) and will launch Chrome for QR login; treat that file as sensitive and delete it when you no longer need the skill.
- Note the optional XIAOHONGSHU_API_BASE env var can redirect network calls — ensure it is not set to an untrusted remote endpoint.
- Run the skill in a controlled environment (or sandbox) if you want additional safety, and remove the ~/.local/share/xhs-research directory after use.
Capability Analysis
Type: OpenClaw Skill
Name: xhs-research
Version: 1.0.0
The xhs-research skill is a comprehensive tool for automated Xiaohongshu market research, featuring sophisticated search, deduplication, and scoring logic in `scripts/xhs_research.py`. While the skill performs high-risk actions such as downloading and executing external binaries from GitHub (`scripts/setup.py`) and managing session cookies (`scripts/login.py`), these behaviors are transparently documented and strictly necessary for the stated purpose of interacting with the Xiaohongshu platform. The instructions in `SKILL.md` are well-structured, focusing on data accuracy and source attribution, with no evidence of malicious intent, data exfiltration, or unauthorized persistence.
Capability Assessment
Purpose & Capability
Name/description describe Xiaohongshu research; required binaries (python3, git), local scripts, QR login flow, and an MCP binary are all consistent with implementing a local search engine + report synthesis. No unrelated credentials or surprising permissions are requested.
Instruction Scope
SKILL.md instructs the agent to generate search keywords, run the included Python scripts, perform a QR login (via a downloaded xiaohongshu-login binary), run a local MCP server, and save reports/cookies to ~/.local/share/xhs-research and ~/Documents/XHS-Research. These actions match the stated task but include storing login cookies and launching a local service and Chrome for QR login (user interaction required).
Install Mechanism
setup.py downloads a release tarball from GitHub (xpzouying/xiaohongshu-mcp) and extracts binaries into ~/.local/share/xhs-research/bin. Downloading release assets from GitHub is standard practice but still executes third‑party binaries on your machine — verify the upstream repo and release integrity before running.
Credentials
No required environment variables or external credentials are declared. The skill will create local files (cookies.json) containing login/session data — this is necessary for its function but is sensitive. Note: the scripts respect an optional XIAOHONGSHU_API_BASE env var which, if set, can change the backend endpoint used by the client.
Persistence & Privilege
always is false and the skill does not request platform-global privileges. It writes files under the user's home directory and runs a local binary server; it does not modify other skills or system-wide agent configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xhs-research - After installation, invoke the skill by name or use
/xhs-research - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
xhs-research v2.0.0 — Major upgrade for 小红书调研工具 with automated research workflows.
- Now supports fully automated 小红书调研: generates search keywords with LLM, runs multi-keyword searches, and auto-creates AI-powered synthesis reports with source links.
- Guided setup and environment checks with clear step-by-step instructions for tool installation, login, and service startup.
- Flexible templates for a wide range of research types (推荐, 调研, 避雷, 对比, 痛点等), ensuring every piece of information is source-linked.
- All reports saved to ~/Documents/XHS-Research/ with user notification and data bias disclaimer included.
- Strong focus on using real user data from 小红书, with strict citation requirements and no unverifiable statements.
- User flow enhanced: after report completion, tailored follow-up suggestions are provided, based on actual research findings.
Metadata
Frequently Asked Questions
What is xhs-research?
小红书调研工具 — 搜索小红书笔记，AI 合成调研报告。 It is an AI Agent Skill for Claude Code / OpenClaw, with 96 downloads so far.
How do I install xhs-research?
Run "/install xhs-research" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is xhs-research free?
Yes, xhs-research is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does xhs-research support?
xhs-research is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created xhs-research?
It is built and maintained by kunhai1994 (@kunhai1994); the current version is v1.0.0.
More Skills