Transform Videos to Markdown: AI Notes for Bilibili, Douyin, YouTube

Transform Videos to Markdown: AI Notes for Bilibili, Douyin, YouTube

This AI agent skill facilitates the conversion of video content from platforms such as Bilibili, Douyin, YouTube, and Xiaohongshu into structured Markdown classroom notes. When users submit video links or sharing codes from these platforms, the skill generates a Markdown (.md) file according to specified templates and quality standards.

What this skill does

• Identifies the video platform from a provided link or sharing code, including bilibili.com, b23.tv, douyin.com, youtube.com, youtu.be, xiaohongshu.com, and xhslink.com.
• For Bilibili: Uses `bili_fetch.py` to access the official API with priority on subtitles, downloading audio or video streams as needed.
• For Douyin: Employs `douyin_fetch.py` to download videos locally for transcription via ASR, with no requirement for login or credentials.
• For YouTube: Utilizes `yt_fetch.py` to prioritize existing subtitles, minimizing media download unless necessary.
• For Xiaohongshu: Uses `xhs_fetch.py` to download video content locally for transcription, with additional requirements for xsec_token in links.
• Outputs formatted Markdown notes using pre-defined templates and performs quality control checks on the output.

Who it is for

• Developers using AI coding agents like Claude Code, Cursor, or Codex.
• Teams requiring efficient transcription and note-taking from video content for educational or review purposes.
• Technical writers and educators looking to streamline video content summarization into structured formats.

Use cases

• Converting educational or tutorial videos from Bilibili into organized Markdown notes for class distribution.
• Automating the creation of meeting summaries from Douyin videos shared in team communications.
• Generating review materials from YouTube educational content for enhanced study sessions.
• Structured conversion of Xiaohongshu video content into notes for project documentation.

Technical details

• Scripts are stored in the skill's `scripts/` directory with configuration in `config.json`.
• Requires Python packages: `yt-dlp`, `youtube-transcript-api`, and `gmssl` for operation.
• Integration with AI agents like Claude Code, Cursor, and Codex for enhanced workflow automation.
• Applies predefined templates from `references/note-template.md` for consistent note formatting.
• ASR terminology correction utilizes `references/asr-glossary.json` for accuracy.
• Compliance with platform terms is required; targets publicly available video content only.

Source & Licence

This package is built on open-source work published by lucky-Luor (lucky-Luor/bilibili-douyin-notes) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.