video

Extract frames, audio, and metadata from video files using ffmpeg and Whisper.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/Jaydpatel01/.github --skill video-jaydpatel01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video
Source: https://github.com/Jaydpatel01/.github/tree/main/skills/video
Command: npx skills add https://github.com/Jaydpatel01/.github --skill video-jaydpatel01

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opencv-python, moviepy, openai-whisper, scenedetect[opencv], imageio[ffmpeg], and includes references (resource) components.

What problem does it solve?

This Skill streamlines the complex and time-consuming tasks associated with video file manipulation and analysis, enabling users to efficiently extract valuable information and transform video content.

Core Features & Use Cases

  • Metadata Extraction: Retrieve details like duration, resolution, codec, and frame rate.
  • Content Analysis: Extract frames, detect scenes, and transcribe speech.
  • Format Conversion & Editing: Convert between formats, trim, and clip videos.
  • Use Case: Automatically extract key frames from a marketing video to generate a storyboard, transcribe the audio for subtitles, and convert the video to a web-optimized format.

Quick Start

Use the video skill to extract all frames from the attached file 'my_vacation.mp4' every 5 seconds.

Frequently Asked Questions about video

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

FAQPage Schema
How do I extract frames from a video for analysis?

You can extract frames from a video for analysis by specifying an interval, such as pulling a frame every 5 seconds. This process utilizes opencv-python and imageio to isolate images for content inspection and storyboarding.

Can I transcribe speech from an mp4 file directly?

Yes, you can transcribe speech from an mp4 file directly. The Skill extracts audio from the video and leverages openai-whisper to convert spoken dialogue into text for subtitles or transcription.

How do I detect scene changes in a video automatically?

To detect scene changes in a video automatically, the Skill applies scenedetect alongside opencv-python. This identifies visual transitions to separate distinct scenes for targeted content analysis.

What is the best way to retrieve video metadata like duration and codec?

The best way to retrieve video metadata like duration and codec is through ffprobe. This process extracts comprehensive file properties including resolution and frame rate for media organization.

Can I convert video formats and trim clips without separate software?

Yes, you can convert video formats and trim clips without separate software. The Skill uses moviepy and ffmpeg to execute format conversion and video clipping directly within your processing pipeline.

Does this video processing approach work for large marketing videos?

This video processing approach works for large marketing videos by combining moviepy and ffmpeg. It handles heavy media files to extract metadata, transcribe audio, and convert formats efficiently.