sort-videos

Transcribe, categorize, and summarize videos using ffmpeg, whisper-cpp, and OCR.

Updated Feb 17, 2026
One-click install
npx skills add https://github.com/tal/plugin-marketplace --skill sort-videos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sort-videos
Source: https://github.com/tal/plugin-marketplace/tree/main/plugins/sort/skills/sort-videos
Command: npx skills add https://github.com/tal/plugin-marketplace --skill sort-videos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, whisper-cpp, jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of transcribing videos, extracting on-screen text, and organizing video content into relevant topics, reducing manual effort in video analysis and categorization.

Core Features & Use Cases

  • Transcription and Summarization: Converts video audio into text and creates detailed summaries for lectures, talks, or long-form content.
  • Content Categorization: Classifies videos into relevant topics and moves files into structured folders for easy retrieval.
  • Quick Start: Use the sort-videos skill to process a downloaded video file by referencing its path or glob pattern, generating a markdown summary, and optionally exporting an audio MP3 for extended listening.

Frequently Asked Questions about sort-videos

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

FAQPage Schema
How do I automate video transcription and categorize the files into folders?

Video transcription and categorization is automated by converting audio to text and extracting on-screen text, then classifying the content into relevant topics and moving files into structured folders for easy retrieval.

How do I extract text from video frames and audio for educational lectures?

To extract text from educational videos, the Skill integrates speech-to-text transcription with visual text analysis techniques, capturing both spoken dialogue and on-screen text from video frames.

Do I need ffmpeg and whisper-cpp to transcribe videos and generate summaries?

Yes, ffmpeg, whisper-cpp, and jq are required dependencies to handle audio extraction, speech-to-text transcription, and JSON data processing for generating markdown summaries.

What is the best way to summarize conference videos and export audio for review?

The best way to summarize conference videos is to process the file by referencing its path, generating a detailed markdown summary, and optionally exporting an audio MP3 for extended listening and review.

Can I process media files using a glob pattern to organize multiple videos at once?

Yes, you can process a downloaded video file by referencing its path or glob pattern, which allows the Skill to handle batch video organization within user-defined folders.

Are there limitations when using OCR frame analysis on long-form media files?

OCR frame analysis extracts on-screen text from long-form media files, but processing extended videos may require significant computational resources and time due to detailed frame-by-frame evaluation.