skills.rest
WingedGuardian
WingedGuardianCOMMUNITY
Explore all skills by this author →
GitHub

video-processing

Download, transcribe, and generate captioned vertical clips from long-form videos.

90|16|Updated Mar 21, 2026
Search Tags:#transcription#yt-dlp#ffmpeg#thumbnail#video-processing#clip#caption
One-click install
npx skills add https://github.com/WingedGuardian/GENesis-AGI --skill video-processing-wingedguardian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video-processing
Source: https://github.com/WingedGuardian/GENesis-AGI/tree/main/src/genesis/skills/video-processing
Command: npx skills add https://github.com/WingedGuardian/GENesis-AGI --skill video-processing-wingedguardian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn long-form videos into ready-to-use outputs: transcripts, short clips, vertical formats with captions, and thumbnails.

Core Features & Use Cases

  • Transcribe long-form content and extract meaningful clips with automatic captions.
  • Produce vertical 9:16 clips with thumbnails suitable for social media.
  • Generate ready-to-share assets for marketing, education, or research scenarios.

Quick Start

Process a given video to generate a 60-second highlight clip with captions and a thumbnail by providing the source URL or file.

Frequently Asked Questions about video-processing

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

FAQPage Schema
How do I transcribe long-form videos and extract short clips with captions?▼

To transcribe videos and extract short clips with captions, you provide a source URL or file to generate a transcript and cut specific segments. This workflow supports YouTube auto-subs, Groq Whisper, OpenAI Whisper, and local Whisper for transcription.

Can I generate vertical 9:16 clips and thumbnails for social media from a YouTube video?▼

Yes, you can generate vertical 9:16 clips and thumbnails for social media from a YouTube video. The workflow downloads the source via yt-dlp, transcribes the audio, and formats the output into vertical 9:16 videos with overlaid captions.

Do I need FFmpeg and yt-dlp installed to process video files and download content?▼

Yes, you need FFmpeg and yt-dlp installed to process video files and download content. FFmpeg handles video clipping, caption burning, and vertical formatting, while yt-dlp manages downloading source videos from platforms like YouTube.

What is the best way to turn long-form video content into ready-to-share marketing assets?▼

The best way to turn long-form video content into ready-to-share marketing assets is to automate the extraction of 60-second highlight clips. This method produces vertical 9:16 outputs with captions and thumbnails suitable for social media campaigns.

Does transcription work with local Whisper or only cloud services like Groq and OpenAI?▼

Transcription works with both local Whisper and cloud services like Groq and OpenAI. You can select local Whisper for offline processing or use Groq Whisper and OpenAI Whisper for cloud-based transcription of your video content.

Related Skills

Explore More Design & Creative Skills→
shekerkammashekerkamma

watch

Download videos, extract timestamped frames, and retrieve synchronized transcripts for analysis.

Community
Advanced
zephyrwang6zephyrwang6
333

content-digest

Convert YouTube, podcasts, interviews, or articles into short-form summaries and long-form narratives.

Community
Advanced
uxjosephuxjoseph
37

/shorts

Automates YouTube video downloading, highlight selection, and rendering of three 9:16 Shorts with subtitles.

Community
Advanced
kjayleekjaylee

video-pro

Render React components to MP4 and perform FFmpeg video edits on a remote MiniPC.

Community
Advanced