Xhs Cli logo

Xhs Cli

Community
jackwener
xhs-cli

Headless-browser-based CLI skill for Xiaohongshu (小红书, RedNote, XHS) to search notes, read posts, browse profiles, like, favorite, comment, and publish from the terminal

Overview

Publisherjackwener
Repositoryxhs-cli
Skill namexhs-cli
Stars
666
Forks
69
Bundled files
16
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jackwener on GitHub. Read the source before you install it.

Installation

Install the Xhs Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jackwener/xhs-cli/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jackwener/xhs-cli.git \
  .claude/skills/xhs-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Xhs Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Xhs Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Xhs Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

[!NOTE] An alternative package xiaohongshu-cli is available, which uses a reverse-engineered API and runs faster. This package (xhs-cli) uses a headless browser (camoufox) approach — slower but more resilient against risk-control detection. Choose whichever best fits your needs.

xhs-cli Skill

A CLI tool for interacting with Xiaohongshu (小红书). Use it to search notes, read details, browse user profiles, and perform interactions like liking, favoriting, and commenting.

Prerequisites

bash
# Install (requires Python 3.8+)
uv tool install xhs-cli
# Or: pipx install xhs-cli

Authentication

All commands require valid cookies to function.

bash
xhs status                     # Check saved login session (no browser extraction)
xhs login                      # Auto-extract Chrome cookies
xhs login --cookie "a1=..."    # Or provide cookies manually

Authentication first uses saved local cookies. If unavailable, it auto-detects local Chrome cookies via browser-cookie3. If extraction fails, QR code login is available.

Command Reference

Search

bash
xhs search "咖啡"              # Search notes (rich table output)
xhs search "咖啡" --json       # Raw JSON output

Read Note

bash
# View note (xsec_token auto-resolved from search cache)
xhs read <note_id>
xhs read <note_id> --comments  # Include comments
xhs read <note_id> --xsec-token <token>  # Manual token
xhs read <note_id> --json

User

bash
# Look up user profile (by internal user_id, hex format)
xhs user <user_id>
xhs user <user_id> --json

# List user's published notes
xhs user-posts <user_id>
xhs user-posts <user_id> --json

# Followers / Following
xhs followers <user_id>
xhs following <user_id>

Discovery

bash
xhs feed                       # Explore page recommended feed
xhs feed --json
xhs topics "旅行"              # Search topics/hashtags
xhs topics "旅行" --json

Interactions (require login)

bash
# Like / Unlike (xsec_token auto-resolved)
xhs like <note_id>
xhs like <note_id> --undo

# Favorite / Unfavorite
xhs favorite <note_id>
xhs favorite <note_id> --undo

# Comment
xhs comment <note_id> "好棒!"

# Delete your own note
xhs delete <note_id>

Favorites

bash
xhs favorites                  # List your favorites
xhs favorites --max 10         # Limit count
xhs favorites --json

Post

bash
xhs post "标题" --image photo1.jpg --image photo2.jpg --content "正文"
xhs post "标题" --image photo1.jpg --content "正文" --json

Account

bash
xhs status                     # Quick saved-session check
xhs whoami                     # Full profile info
xhs whoami --json
xhs login                      # Login
xhs logout                     # Clear cookies

JSON Output

Major query commands support --json for machine-readable output:

bash
xhs search "咖啡" --json | jq '.[0].id'           # First note ID
xhs whoami --json | jq '.userInfo.userId'          # Your user ID
xhs favorites --json | jq '.[0].displayTitle'      # First favorite title

Common Patterns for AI Agents

bash
# Get your user ID for further queries
xhs whoami --json | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('userInfo',{}).get('userId',''))"

# Search and get note IDs (xsec_token auto-cached for later use)
xhs search "topic" --json | python3 -c "import sys,json; [print(n['id']) for n in json.load(sys.stdin)[:3]]"

# Check login before performing actions
xhs status && xhs like <note_id>

# Read a note with comments for summarization
xhs read <note_id> --comments --json

Error Handling

  • Commands exit with code 0 on success, non-zero on failure
  • Error messages are prefixed with ❌
  • Login-required commands show clear instruction to run xhs login
  • xsec_token is auto-resolved from cache; manual --xsec-token available as fallback

Safety Notes

  • Do not ask users to share raw cookie values in chat logs.
  • Prefer auto-extraction via xhs login over manual cookie input.
  • If auth fails, ask the user to re-login via xhs login.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Xhs Cli AI skill do?

Headless-browser-based CLI skill for Xiaohongshu (小红书, RedNote, XHS) to search notes, read posts, browse profiles, like, favorite, comment, and publish from the terminal

Why use Xhs Cli on TypingMind?

Because you install it once and use it with any model. Xhs Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Xhs Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jackwener/xhs-cli/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Xhs Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Xhs Cli?

As many as you like. As long as a model supports skills, you can use Xhs Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Xhs Cli AI skill free?

Yes. It is published on GitHub by jackwener under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇