youtube-video-analyzer
por sdrabent
Coding Agents & IDEsResumo
Multimodal YouTube video analysis through both audio (transcript) and visual (frame extraction + image analysis)
Descrição
O que esta skill faz
Analyzes YouTube videos through both transcript extraction and frame-by-frame visual analysis. Synchronizes spoken content with extracted video frames by timestamp, enabling step-by-step guides where on-screen UI elements, code, and diagrams are captured alongside what is said.
Unlike transcript-only YouTube tools, it captures visual content, so information shown on screen but not spoken, such as specific button names, menu paths, or code, is not lost.
Quando usá-la
- Building step-by-step guides from software tutorial videos
- Extracting code shown on screen but not read aloud
- Documenting exact UI click paths from product demo videos
- Summarizing long explainer videos with timestamped visual anchors
- Capturing tool usage and hand positions from physical howto videos
Exemplo de fluxo de trabalho
User asks: Create a step-by-step guide from this YouTube tutorial: https://youtube.com/watch?v=abc123
- 1
Fetches video metadata (title, duration, ID) using yt-dlp
- 2
Extracts timestamped transcript via yt-dlp JSON dump and curl
- 3
Downloads video at 720p and extracts keyframes at adaptive intervals using ffmpeg
- 4
Synchronizes each frame with the corresponding transcript segment by timestamp
- 5
Reads each frame image alongside transcript text to generate a structured step-by-step guide
A markdown step-by-step guide with each action timestamped and annotated with visual descriptions of what appears on screen at that moment
Requisitos
- ffmpeg
- yt-dlp
Instalação
clawhub install sdrabent/youtube-video-analyzerExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.