video-processor

Transcribe videos, generate chapters, thumbnails, and social media images.

2|Updated May 8, 2026
One-click install
npx skills add https://github.com/seanrobertwright/archon-workflow-studio --skill video-processor-seanrobertwright
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-processor
Source: https://github.com/seanrobertwright/archon-workflow-studio/tree/main/.agents/skills/video-processor
Command: npx skills add https://github.com/seanrobertwright/archon-workflow-studio --skill video-processor-seanrobertwright

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, uv, openai, gemini, replicate, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the transcription, chapter generation, and social media graphic creation from video files, streamlining content production workflows.

Core Features & Use Cases

  • Transcription & Chapters: Convert video clips into timestamped transcripts, SRT subtitles, and generate AI-based YouTube chapters.
  • Thumbnail Generation: Create AI-generated thumbnails with face references or style matching for YouTube videos.
  • Social Media Graphics: Generate professional LinkedIn post images and customizable images for platforms like Instagram, Twitter, or Facebook.
  • Use Case: Content creators can transcribe long videos, produce engaging thumbnails, and prepare social media snippets without manual effort, enhancing productivity.

Quick Start

Use the video-processor to transcribe a folder of videos, then generate thumbnails or social images with descriptive prompts.

Frequently Asked Questions about video-processor

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

FAQPage Schema
How do I automate video transcription and YouTube chapter generation?

Automate video transcription and YouTube chapter generation by processing video files with Whisper to produce timestamped transcripts and SRT subtitles. The workflow analyzes the transcript to segment the video into logical chapters, producing AI-based chapter markers without manual effort.

Can I generate AI thumbnails for YouTube videos using face references?

Yes, you can generate AI thumbnails for YouTube videos using face references or style matching. By providing descriptive prompts, the workflow leverages Gemini image generation to create customized, engaging thumbnails tailored to your video content.

Do I need FFmpeg installed to process videos for social media graphics?

Yes, FFmpeg is required to process videos for social media graphics. It handles the underlying video file processing required to extract the content, which is then used to generate professional images for platforms like LinkedIn, Instagram, Twitter, or Facebook.

What is the best way to convert long videos into social media snippets?

The best way to convert long videos into social media snippets is using an automated multi-step workflow. It transcribes the video, extracts key segments, and generates customizable social media graphics, streamlining content production for digital marketers and content creators.

How does AI image generation work for creating LinkedIn post images?

AI image generation for LinkedIn post images works by taking descriptive prompts derived from your video content and passing them to Gemini. This produces professional, platform-specific graphics suitable for content creators and digital marketers without manual design.