xiaohongshu-fetch

Retrieve Xiaohongshu notes and write structured records to Feishu Bitable.

1.8k|235|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/mcncarl/yichen-skills --skill xiaohongshu-fetch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xiaohongshu-fetch
Source: https://github.com/mcncarl/yichen-skills/tree/main/xiaohongshu-fetch
Command: npx skills add https://github.com/mcncarl/yichen-skills --skill xiaohongshu-fetch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This skill automates the retrieval and structuring of Xiaohongshu notes (video and image-text) and sediments them into Feishu multi-dimensional tables for organized content management and publishing workflows.

Core Features & Use Cases

  • Video notes processing: extract video URL, ASR transcript, and segmentation; write results to the video benchmark library.
  • Image-text notes processing: OCR and summarize image content; populate the social-trend topic library or a user-specified table.
  • Safe configuration: reads target table settings from private config or environment variables; avoids hard-coded tokens or credentials.

Quick Start

将小红书笔记链接发送给 AI,并指示系统将笔记元数据和媒体沉淀到飞书表格的默认目标表中。

Frequently Asked Questions about xiaohongshu-fetch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically extract Xiaohongshu notes and save them to Feishu Bitable?

Automating Xiaohongshu notes extraction to Feishu Bitable involves parsing note URLs, transcribing video ASR or summarizing image-text OCR, and writing structured records directly into your target table.

How does ASR transcription work for Xiaohongshu video notes?

ASR transcription for Xiaohongshu video notes works by extracting the video URL, processing the audio to generate a transcript, segmenting the results, and ingesting the structured data into the video benchmark library.

Can I use this to process image-text notes with OCR and summarize the content?

You can process image-text notes by applying OCR to extract text from images, summarizing the content, and populating the results into your social-trend topic library or a user-specified Feishu table.

Do I need to hardcode Feishu API tokens in the script to ingest media?

You do not need to hardcode Feishu API tokens, as the skill reads target table settings from private configurations or environment variables, ensuring sensitive credentials are never embedded in logs.

What is the best way to handle media download failures when scraping Xiaohongshu content?

Handling media download failures when scraping Xiaohongshu content is managed through resilient fallbacks during the download process, ensuring the retrieval of note media remains robust before writing to Feishu Bitable.