BeClaude

claude-video-vision

New
665Community RegistryGeneralby Jordan Vasconcelos

Give Claude the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via Gemini API, local Whisper, or OpenAI API. Multimodal perception layer for Claude Code.

Install & Usage

1
Create the skills directory
mkdir -p .claude/skills
2
Download the skill file
mkdir -p .claude/skills && curl -o .claude/skills/claude-video-vision.md https://raw.githubusercontent.com/jordanrendric/claude-video-vision/main/SKILL.md
3
Invoke in Claude Code
/claude-video-vision
View source on GitHub
apivideovisionmultimodalffmpegwhispergeminiperception

Frequently Asked Questions

What is claude-video-vision?

Give Claude the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via Gemini API, local Whisper, or OpenAI API. Multimodal perception layer for Claude Code.

How to install claude-video-vision?

To install claude-video-vision, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /claude-video-vision.

What is claude-video-vision best for?

claude-video-vision is a community categorized under General. It is designed for: api, video, vision, multimodal, ffmpeg, whisper, gemini, perception. Created by Jordan Vasconcelos.