yt-shorts-for-x

Extract, transcribe, classify, crop, caption, and upload short clips from YouTube or mp4 files to X.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/akshatdalton/skills --skill yt-shorts-for-x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: yt-shorts-for-x
Source: https://github.com/akshatdalton/skills/tree/main/yt-shorts-for-x
Command: npx skills add https://github.com/akshatdalton/skills --skill yt-shorts-for-x

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, ffmpeg, faster-whisper, PySceneDetect, mediapipe, gdrive-api, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of extracting short, captioned clips from YouTube videos and preparing them for posting on platforms like X.

Core Features & Use Cases

  • Clip Extraction: Automatically generates captioned 9:16 clips from YouTube URLs or local mp4 files.
  • Captioning: Burns captions into the clips for better engagement.
  • Verification: Automatically scans the clips for quality assurance before uploading.
  • Upload: Uploads the clips to Google Drive and provides a URL for posting on X.
  • Use Case: If you want to create engaging vertical content for X from a long YouTube video, use this skill to quickly extract, caption, and prepare your content for posting.

Quick Start

Use the yt-shorts-for-x skill to extract 3 captioned clips from 'example_video.mp4' for posting on X.

Frequently Asked Questions about yt-shorts-for-x

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

FAQPage Schema
How do I extract viral clips from YouTube videos for X?

To extract viral clips from YouTube videos, this Skill uses PySceneDetect for scene detection and faster-whisper for transcription to identify engaging segments. It then crops, captions, and uploads these short clips to prepare them for posting on X.

Can I burn captions into vertical video clips automatically?

Yes, you can burn captions into vertical video clips automatically using ffmpeg. The Skill transcribes the audio with faster-whisper and then renders the text directly onto the 9:16 video format to improve viewer engagement.

Do I need Python and ffmpeg to generate captioned shorts from local mp4 files?

Yes, you need Python and ffmpeg installed to process local mp4 files. The Skill also requires faster-whisper, PySceneDetect, MediaPipe FaceLandmarker, and Google Drive API access to transcribe, classify, crop, and upload the generated clips.

How does face tracking work when cropping YouTube clips to 9:16?

Face tracking during the 9:16 cropping process works by using MediaPipe FaceLandmarker. It detects facial landmarks within the video frames to ensure the speaker remains centered and properly framed within the vertical short clip extraction.

What is the best way to upload generated video shorts to Google Drive for posting?

The best way to upload generated video shorts to Google Drive is through the gdrive-api. The Skill handles the cloud storage operations automatically, providing a shareable URL for each clip so you can quickly post the content on X.

Are there limitations when using faster-whisper for YouTube video transcription?

When using faster-whisper for YouTube video transcription, processing speed and accuracy depend on your local hardware capabilities. The Skill requires downloading the YouTube video or loading a local mp4 file before the AI-driven transcription can begin.