skills.rest
HuaiminHuang
HuaiminHuangCOMMUNITY
Explore all skills by this author →
GitHub

video-tutor

Convert video lectures into structured Chinese teaching notes with transcripts and key frames.

Updated Apr 12, 2026
Search Tags:#pdf#video#transcripts#latex#frame-extraction#teaching-notes
One-click install
npx skills add https://github.com/HuaiminHuang/personal-skills-for-openclaw --skill video-tutor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video-tutor
Source: https://github.com/HuaiminHuang/personal-skills-for-openclaw/tree/main/video-tutor
Command: npx skills add https://github.com/HuaiminHuang/personal-skills-for-openclaw --skill video-tutor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt_dlp, ffmpeg, faster-whisper, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Turn video lectures into structured Chinese teaching notes with transcripts, key frames, diagrams, formulas, and code, delivered in Markdown or LaTeX/PDF.

Core Features & Use Cases

  • Input: video URL from YouTube, Bilibili, or other platforms; outputs a figure-rich teaching note suitable for study, review, or classroom use.
  • Subtitle handling: prefers platform CC subtitles; falls back to Whisper transcription when CC subtitles are unavailable; supports multi-part videos and long-form content; extracts video cover and key frames; outputs Markdown or LaTeX/PDF.
  • Output formats: Markdown or LaTeX/PDF reports with time-provenance frames and integrated figures, diagrams, and formulas.

Quick Start

Provide a video URL and choose the output format to generate a structured Chinese teaching note with transcripts, key frames, diagrams, formulas, and code.

Frequently Asked Questions about video-tutor

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

FAQPage Schema
How do I turn video lectures into structured Chinese teaching notes?▼

Turn video lectures into structured Chinese teaching notes by providing a video URL from platforms like YouTube or Bilibili. The workflow extracts subtitles, key frames, diagrams, formulas, and code to generate Markdown or LaTeX/PDF reports.

How does subtitle extraction work when CC subtitles are unavailable?▼

Subtitle extraction prefers platform-provided CC subtitles but automatically falls back to faster-whisper transcription when they are unavailable. This ensures multi-part videos and long-form content are fully transcribed for note generation.

Can I generate LaTeX or PDF reports from YouTube and Bilibili videos?▼

Yes, you can generate LaTeX or PDF reports from YouTube and Bilibili videos. The workflow outputs Markdown by default but supports optional LaTeX/PDF rendering with time-provenance frames and integrated figures.

What's the best way to extract key frames and diagrams from educational videos?▼

Extract key frames and diagrams from educational videos using the integrated frame-extraction workflow. It captures figure-rich visual content with time-proven metadata, embedding them directly into structured teaching notes.

Do I need ffmpeg and faster-whisper to transcribe long-form multi-part videos?▼

Yes, ffmpeg and faster-whisper are required dependencies for frame extraction and audio transcription. They enable processing long-form and multi-part videos when platform CC subtitles are missing.

Related Skills

Explore More Education & Research Skills→
imlewcimlewc
153

video-to-subtitle-summary

Converts online or local videos to subtitles and generates AI summaries.

Community
Intermediate
lanejlanej
40

presenterm

Convert Markdown files into interactive terminal presentations with themes, diagrams, and exports.

Community
Intermediate
video-production-buddyvideo-production-buddy
602

video-understand

Analyze local videos with ffmpeg frame extraction and Whisper transcription.

Official
Intermediate
jin-bojin-bo
94

ocr

Extract text from image files using the Qwen VL OCR model.

Community
Intermediate