clip-hand-skill

Transcribe long-form videos and extract key segments into short clips.

3|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/ybsa/sovereign-kernel --skill clip-hand-skill-ybsa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clip-hand-skill
Source: https://github.com/ybsa/sovereign-kernel/tree/main/crates/sk-hands/bundled/clip
Command: npx skills add https://github.com/ybsa/sovereign-kernel --skill clip-hand-skill-ybsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of short, engaging video clips from longer-form content, streamlining social media content production.

Core Features & Use Cases

  • Automated Clipping: Identifies and extracts compelling segments from videos.
  • Transcription & Captions: Generates accurate captions for accessibility and engagement.
  • Publishing: Optionally shares clips to platforms like Telegram and WhatsApp.
  • Use Case: Turn a long webinar or podcast into multiple 30-second viral clips for TikTok or Instagram Reels, complete with captions and a voice-over.

Quick Start

Use the clip-hand skill to download a YouTube video and create three short clips with captions.

Frequently Asked Questions about clip-hand-skill

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

FAQPage Schema
How do I turn long-form video content into viral shorts automatically?

To turn long-form video content into viral shorts, this Skill downloads videos, transcribes the audio, and analyzes the text to extract compelling segments. It uses ffmpeg and yt-dlp to process and clip video files automatically.

How does transcription work for generating video captions?

Transcription for video captions works by processing the downloaded video's audio track through supported speech-to-text providers. The transcribed text is then analyzed to identify key segments and generate accurate captions for your clips.

Can I use yt-dlp and ffmpeg to download and clip YouTube videos for social media?

Yes, you can use yt-dlp and ffmpeg to download and clip YouTube videos for social media. The Skill handles cross-platform execution to download source content and extract specific short segments suitable for platforms like TikTok.

Does the video clipping process support publishing clips directly to Telegram and WhatsApp?

Yes, the video clipping process supports publishing clips directly to Telegram and WhatsApp. After extracting and generating your short video segments, the Skill can optionally share the final clips to these messaging platforms.

What is the best way to extract key segments from a podcast or webinar?

The best way to extract key segments from a podcast or webinar is to analyze the video's transcription for compelling moments. This Skill automates that by transcribing the audio, identifying highlights, and cutting the video into short clips.

Are there limitations on speech-to-text providers for video editing and transcription?

There are no specific limitations mentioned on speech-to-text providers for video editing and transcription. The Skill supports multiple speech-to-text providers to ensure accurate transcription and caption generation for your video clips.