hetpatel-11

Video To LLM Context Extractor — AI skill for Claude Code

AI community

Turn any video into a detailed, LLM-ready PDF document.

How to install Video To LLM Context Extractor

This entry records only its repository, not the path inside it, so there is no exact command to give. Open hetpatel-11/Video-to-LLM-Context-Extractor and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Video To LLM Context Extractor does

Turn any video into a detailed, LLM-ready PDF document. Perfect for feeding visual and transcribed context into models like Claude, GPT, and Gemini.

Alternatives in AI

Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
Matlab MCP Server — Run MATLAB® using AI applications with the official MATLAB MCP Server from MathWorks® 1.4k ★

README

🚀 Video-to-LLM Context Extractor 🚀

**Turn any video into a detailed, LLM-ready PDF document. Perfect for feeding visual and transcribed context into models like Claude, GPT, and Gemini.**

Follow me on X:

✨ Core Features

🖼️ Frame-by-Frame Capture: Extracts video frames at set intervals to create a visual storyboard of the content.
🎙️ Accurate Audio Transcription: Converts all spoken words into a written transcript using robust speech recognition.
📄 LLM-Optimized PDF Generation: Intelligently combines captured frames and the audio transcript into a single, easy-to-read PDF.
🧠 Handles Videos of Any Length: For longer videos, the audio is automatically chunked and processed in parallel for speed and reliability.
✂️ Automatic PDF Splitting: To ensure compatibility with LLMs, output is automatically split into multiple files if the content is extensive.
🎨 Sleek Glassmorphic UI: A modern, beautiful desktop interface that's a pleasure to use.
🌐 Cross-Platform: Built with Electron to run on Windows, macOS, and Linux.

🤔 How It Works: The 30MB Limit Explained

Large Language Models often have strict limits on the size of files you can upload. For instance, **Anthropic's Claude models generally accept PDFs up to around 30MB.**

This tool is designed with that constraint in mind. Here's the process:

You select a video file.
The application begins extracting frames and transcribing the audio.
As the PDF is being built, the tool constantly monitors its size.
If the PDF is about to exceed a safe limit (set to 28MB to be cautious), it saves the current PDF and starts a new one.
This results in a set of sequentially numbered PDF files (e.g., my_video_1.pdf, my_video_2.pdf, etc.) for very long videos.

This allows you to process hours of vid