video

Extract summaries and transcripts from YouTube videos and local media files.

6|2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/filipexyz/ravi --skill video-filipexyz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video
Source: https://github.com/filipexyz/ravi/tree/main/src/plugins/internal/ravi-system/skills/video
Command: npx skills add https://github.com/filipexyz/ravi --skill video-filipexyz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp.

What problem does it solve?

This skill solves the time-consuming challenge of manually watching long videos to extract information, summaries, or transcriptions by automating the analysis process.

Core Features & Use Cases

  • Multi-Source Analysis: Processes both public YouTube URLs and local video files.
  • Intelligent Fallback: Uses efficient subtitle extraction via yt-dlp by default, switching to Gemini AI for visual analysis or when subtitles are unavailable.
  • Use Case: Quickly generate a structured markdown report containing a summary, key topics, and a full transcript for a one-hour technical tutorial or meeting recording.

Quick Start

Use the video skill to analyze the content of the provided YouTube URL and save the output to a markdown file.

Frequently Asked Questions about video

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

FAQPage Schema
How do I extract a summary and transcript from a YouTube video?

To extract a summary and transcript from a YouTube video, the skill parses subtitles via yt-dlp and uses Gemini AI for visual analysis, generating a structured markdown report with key topics and full text.

Can I analyze local video files for transcription and visual descriptions?

Yes, you can analyze local video files for transcription and visual descriptions. The skill processes local media using multimodal AI analysis to provide timestamped visual descriptions and structured topic extraction.

Do I need a Gemini API key to analyze video content?

Yes, a configured Gemini API key is required to analyze video content. It enables advanced multimodal visual analysis and serves as an intelligent fallback when default subtitle extraction is unavailable.

What is the best way to get timestamped topics from a long technical tutorial?

The best way to get timestamped topics from a long technical tutorial is using automated transcription and structured topic extraction, which processes subtitle data to create a structured markdown report.

How does video analysis work when subtitles are unavailable?

When subtitles are unavailable, video analysis works by switching to Gemini AI for multimodal processing, allowing the system to perform visual analysis and fallback transcription directly on the media file.