chenxiachan/xhs-claude-skills

Claude Code slash commands for extracting Xiaohongshu posts into Obsidian notes

What it solves

It automates the process of converting Xiaohongshu (Red) posts into structured, actionable notes for Obsidian. Instead of manual copying, it extracts text, images, and video content, transforming them into a format designed for quick decision-making and knowledge management.

How it works

The project operates as a plugin for Claude Code. It uses browser cookies for authentication and makes HTTP requests to extract data from the platform's initial state. For content processing, it uses Claude's multimodal capabilities for image OCR and prioritizes embedded subtitles for videos, falling back to local Whisper transcription via mlx-whisper if subtitles are unavailable. The final output is saved as Markdown files in a specified Obsidian vault folder.

Who it’s for

Users of Claude Code and Obsidian who curate content from Xiaohongshu and want to integrate social media insights into their personal knowledge base without manual data entry.

Highlights

  • Multimodal Extraction: Supports text, image OCR, and video transcription.
  • Seamless Integration: Directly saves formatted notes into Obsidian vaults.
  • Context-Aware: Uses Claude Code's memory to automatically personalize the "Connection to me" section of each note.
  • Lightweight Architecture: Requires no MCP servers or headless browsers, relying on simple HTTP requests and cookies.

Related

  • Project
    huangkiki/dailypaper-skills

    A set of Claude Code skills that automates the discovery, filtering, and structured note-taking for academic papers, integrating with arXiv, HuggingFace, and Obsidian.

  • Project
    jordanrendric/claude-video-vision

    A Claude Code plugin that enables video understanding by extracting frames and transcribing audio via local or cloud backends.

  • Project
    taoufik123-collab/claude-watch

    A Claude skill that enables the AI to watch videos from URLs or local files by extracting key frames and transcripts for multimodal analysis.

  • Project
    AgriciDaniel/claude-obsidian

    A local-first knowledge system for Claude Code and Obsidian that turns source material into linked, source-cited notes while maintaining full user ownership of files.

  • Project
    mengke-wang/xiaohongshu-ai-workbench

    A collection of modular AI workflows (Codex Skills) for Xiaohongshu operations, helping creators systematically optimize their profiles, content planning, and conversion paths.