white0dew/XiaohongshuSkills

支持小红书自动发布、自动评论、自动检索的 Skill。支持 OpenClaw、Codex、CC 等

What it solves

This project provides a command-line interface to automate interactions with the Xiaohongshu (RED) platform. It helps users streamline repetitive tasks like publishing content, managing multiple accounts, and retrieving data from the platform without manual browser navigation.

How it works

It uses the Chrome DevTools Protocol (CDP) to control a Google Chrome browser instance. By interacting directly with the browser's internal protocols, it can fill out forms, upload media, handle login sessions, and extract data from the platform's DOM. It supports both a visible browser mode for manual verification and a "headless" mode for background automation.

Who it’s for

This tool is intended for developers or power users who need to automate Xiaohongshu workflows. It is particularly useful for those looking to integrate Xiaohongshu actions into larger agentic workflows, such as those supported by Claude Code or OpenCode.

Highlights

  • Automated Publishing: Handles titles, text, and media uploads (images/videos) with support for auto-tagging.
  • Multi-Account Management: Manages multiple accounts with isolated cookies and easy switching.
  • Data Extraction: Retrieves feed lists, note details, comments, and user profile snapshots.
  • Interaction Tools: Performs actions like liking, bookmarking, commenting, and replying to notes.
  • Flexible Execution: Supports headless background operation, remote CDP connections, and local login state caching.

Related

  • Project
    huangjunsen0406/py-xiaozhi

    py-xiaozhi is a cross-platform, asynchronous Python framework that enables real-time voice and vision AI interactions on desktop and embedded hardware.

  • Project
    sugarforever/chat-ollama

    An agentic CLI application that allows AI agents to interact with your local workspace by reading, searching, and editing files using local or hosted models.

  • Project
    wang2122/sprix-sage-router

    A decision layer for Agent-to-Agent networks that optimizes mid-execution task rerouting by evaluating whether to continue, collaborate, or hand off based on current progress and artifact portability.

  • Project
    mnemosyne-oss/mnemosyne

    Mnemosyne is an open‑source, SQLite‑backed memory layer for LLM agents. It offers a local‑first, zero‑cloud solution with a Python SDK, a built‑in MCP server, and optional encrypted sync. The system stores facts, embeddings, and temporal triples using a three‑tier BEAM architecture (working, episodic, triple‑store) and performs hybrid vector‑keyword search inside SQLite. It integrates with many agent platforms (Claude Code, Cursor, OpenWebUI, Hermes, etc.) and runs with a single `pip install` and minimal resources.