← Back to Skills Marketplace
laosuan

Xiaohongshu CLI

by laosuan · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
384
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install jackwener-xhs-cli
Description
Install and use the `xhs-cli` terminal client for Xiaohongshu (小红书, RedNote, XHS). Use when Codex needs shell-driven Xiaohongshu operations such as checking...
README (SKILL.md)

Xiaohongshu CLI

Use this skill for terminal-first Xiaohongshu work through xhs-cli. Prefer shell commands over browser automation when the task fits the CLI.

Quick Start

  1. Check whether xhs is already installed with xhs --version.
  2. If it is missing, install it with uv tool install xhs-cli.
  3. If it is present but outdated, prefer uv tool upgrade xhs-cli.
  4. Check auth with xhs status.
  5. If auth is missing or stale, run xhs login.
  6. Prefer --json when results will be parsed, summarized, or reused in later commands.

Install

Prefer uv:

uv tool install xhs-cli
uv tool upgrade xhs-cli

Fallback to pipx if uv is unavailable:

pipx install xhs-cli
pipx upgrade xhs-cli

Only use a source checkout when the user is explicitly developing or patching the CLI itself:

git clone https://github.com/jackwener/xhs-cli.git
cd xhs-cli
uv sync

Auth

Prefer xhs login first. It tries saved cookies, then local Chrome cookies, then QR login.

Use these checks in order:

xhs status
xhs login
xhs whoami --json

Do not ask the user to paste raw cookies into chat logs. Only use xhs login --cookie ... if the user explicitly wants manual cookie input and can provide it locally.

Core Workflows

Search and Read

xhs search "coffee"
xhs search "coffee" --json
xhs read NOTE_ID
xhs read NOTE_ID --comments --json

Use search first when the user needs candidate notes. Use read after a note ID is known.

Profile and Network

xhs whoami --json
xhs user USER_ID --json
xhs user-posts USER_ID --json
xhs followers USER_ID --json
xhs following USER_ID --json

Use whoami --json to discover the current account's internal userId.

Feed, Topics, and Favorites

xhs feed --json
xhs topics "travel" --json
xhs favorites --max 10 --json

Use feed for recommendation browsing. Use topics for hashtag discovery. Use favorites to inspect saved items.

Interaction

Run xhs status before write actions. For note actions, prefer working from IDs already returned by search, feed, or read.

xhs like NOTE_ID
xhs like NOTE_ID --undo
xhs favorite NOTE_ID
xhs favorite NOTE_ID --undo
xhs comment NOTE_ID "Helpful post."
xhs delete NOTE_ID

Publish

xhs post "Title" --image ./cover.jpg --content "Body text"
xhs post "Title" --image ./a.jpg --image ./b.jpg --content "Body text" --json

Use post only after auth is confirmed.

Response Style

Lead with the exact xhs command to run. Keep flags minimal. Prefer a short happy-path command before optional variants. If the user still needs IDs, guide them to search, feed, or whoami --json first.

Reference

Read references/commands.md when the user needs:

  • full command coverage
  • JSON-oriented examples
  • installation variants
  • publish examples
  • troubleshooting guidance
Usage Guidance
This skill is an instruction-only helper for the xhs-cli terminal tool and appears consistent with that purpose. Before installing or allowing an agent to use it, confirm you trust the upstream project (check the GitHub repo and PyPI package), prefer interactive login flows (avoid pasting cookies into chat), and be aware that the CLI may read local browser session cookies to authenticate. Because the CLI can perform writes (post, comment, delete), only grant the agent permission to run these commands if you want it to act on your account. If you are uncomfortable with automated account actions, restrict the agent from invoking the skill autonomously or require explicit approval for write operations.
Capability Analysis
Type: OpenClaw Skill Name: jackwener-xhs-cli Version: 0.1.0 The skill facilitates the installation and operation of the `xhs-cli` tool, which involves high-risk capabilities such as installing external software from PyPI (`uv tool install xhs-cli`) and accessing local Chrome browser cookies for authentication (`xhs login`). While these actions are plausibly necessary for the stated purpose of managing a Xiaohongshu account and the instructions in `SKILL.md` include a security-positive warning against pasting raw cookies into chat logs, the combination of automated package installation and credential extraction from the local filesystem meets the threshold for a suspicious classification under the provided criteria.
Capability Assessment
✓ Purpose & Capability
The name and description match the runtime instructions: all commands, install suggestions (uv, pipx), and repo references point to a Xiaohongshu terminal client. There are no unrelated env vars, binaries, or config paths requested.
ℹ Instruction Scope
The SKILL.md restricts actions to installing and using xhs-cli and documents read/write operations (search, read, like, comment, post, delete). It notes that xhs login may try saved/local Chrome cookies and that manual cookie input should not be pasted into chat — this is relevant because the CLI may access local browser session data. The instructions do not direct the agent to exfiltrate data to third-party endpoints outside the CLI’s normal operations.
✓ Install Mechanism
This is instruction-only; no install spec included. Suggested installs are via 'uv tool install' or 'pipx', and a GitHub checkout is given only for development — all are standard, low-risk installation routes. No arbitrary download URLs or extract operations are used in the skill itself.
ℹ Credentials
The skill does not request environment variables or credentials. However, the CLI workflow can access or reuse local browser cookies/session state for authentication and can perform account write actions; users should be aware that local cookie access and authenticated operations are expected behaviors of the CLI and require user consent.
✓ Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent inclusion or modify other skills. The agent may invoke the skill autonomously (platform default), and because the CLI supports write operations, administrators should be mindful of letting an autonomous agent perform account actions.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install jackwener-xhs-cli
  3. After installation, invoke the skill by name or use /jackwener-xhs-cli
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial OpenClaw skill wrapping jackwener/xhs-cli.
Metadata
Slug jackwener-xhs-cli
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Xiaohongshu CLI?

Install and use the `xhs-cli` terminal client for Xiaohongshu (小红书, RedNote, XHS). Use when Codex needs shell-driven Xiaohongshu operations such as checking... It is an AI Agent Skill for Claude Code / OpenClaw, with 384 downloads so far.

How do I install Xiaohongshu CLI?

Run "/install jackwener-xhs-cli" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Xiaohongshu CLI free?

Yes, Xiaohongshu CLI is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Xiaohongshu CLI support?

Xiaohongshu CLI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Xiaohongshu CLI?

It is built and maintained by laosuan (@laosuan); the current version is v0.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments