Analyze videos with frame extraction and audio context in Claude Code

SkillMedia

This skill lets your AI in Claude Code watch and understand videos. It extracts frames to see what is on screen, transcribes the audio to capture what is said, and then answers your questions about the video. It works with video files on your computer as well as YouTube URLs.

Available today. Use it from your connected AI after setup.

No other account needed.

After adding it, share a local video file or a YouTube URL and ask your AI what you want to know about it.

Then ask your AI: use the Analyze videos with frame extraction and audio context in Claude Code skill

What your AI can do with it

Extract frames from a video to see what happens on screen
Transcribe the audio to capture what is said
Answer questions about video files stored on your computer
Answer questions about YouTube videos
Explain a video using both what is shown and what is said

What this skill tells your AI

The instructions your AI receives, as published by agentskillexchange/skills in skills/analyze-videos-with-frame-extraction-and-audio-context-in-claude-code/SKILL.md and read by ahel’s review.

Give Claude Code a video perception layer that extracts frames, transcribes audio, and lets Claude answer questions about local videos or YouTube URLs.

Prerequisites

Claude Code, Node.js 20+, ffmpeg, optional yt-dlp, Gemini API or Whisper/OpenAI audio backend

Installation

Use the upstream install or setup path that matches your environment:

git clone https://github.com/jordanrendric/claude-video-vision.git

Requirements and caveats from upstream:

| Local (Whisper) | whisper.cpp or Python openai-whisper | Free, fully offline | brew install whisper-cpp + auto model download |
│ MCP Server (Node.js) │
Node.js 20+ (for the MCP server)

Basic usage or getting-started notes: