video-analyze

Extract frames from videos and transcribe audio with Whisper.

4|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/hwj123hwj/custom-skills --skill video-analyze-hwj123hwj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-analyze
Source: https://github.com/hwj123hwj/custom-skills/tree/main/skills/video-analyze
Command: npx skills add https://github.com/hwj123hwj/custom-skills --skill video-analyze-hwj123hwj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, ffmpeg, whisper, torch, openai-whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently analyzing video content by providing frame extraction and automatic speech recognition (ASR) capabilities, transforming visual and auditory information into usable data.

Core Features & Use Cases

  • Frame Extraction: Extracts keyframes from videos to visualize content and identify important scenes.
  • ASR Transcription: Converts video audio into text, enabling textual analysis and searching.
  • Use Case: Consider a scenario where you need to review a series of tutorial videos. This skill can automatically extract frames and transcribe the audio for quick reference.

Quick Start

To analyze the video 'tutorial.mp4', use the video-analyze skill with the command: uv run va extract --file /path/to/tutorial.mp4

Frequently Asked Questions about video-analyze

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

FAQPage Schema
How do I extract frames and transcribe audio from a video file?

To extract frames and transcribe audio from a video file, you need a tool that combines frame extraction with ASR transcription. This Skill processes video data to visualize key scenes and convert spoken audio into searchable text.

Do I need Python and ffmpeg to perform ASR transcription on video content?

Yes, you need Python and ffmpeg to perform ASR transcription on video content. The processing workflow relies on ffmpeg for handling video files and Whisper for automatic speech recognition to convert audio into text.

Can I use a custom ASR model to transcribe video audio into text?

Yes, you can use a custom ASR model to transcribe video audio into text. The Skill supports automatic speech recognition via openai-whisper, allowing you to integrate custom models for tailored transcription results.

What is the best way to analyze large volumes of tutorial videos?

The best way to analyze large volumes of tutorial videos is to automate frame extraction and ASR transcription. This process transforms visual and auditory information into usable data for quick reference and textual analysis.

How does Whisper handle ASR transcription for video analysis?

Whisper handles ASR transcription for video analysis by converting video audio tracks into text. This allows educators and researchers to perform textual analysis and search through spoken content efficiently.

Are there limitations when extracting keyframes from videos for content analysis?

Extracting keyframes from videos for content analysis depends on having proper ffmpeg and Python dependencies configured. Users must ensure their environment supports torch and openai-whisper to process large volumes of video data smoothly.