clip-hand-skill

Turns long videos into shareable shorts with yt-dlp, Whisper SRT captions, and vertical crops via ffmpeg.

10|7|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/librefang/librefang-registry --skill clip-hand-skill-librefang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clip-hand-skill
Source: https://github.com/librefang/librefang-registry/tree/main/hands/clip
Command: npx skills add https://github.com/librefang/librefang-registry --skill clip-hand-skill-librefang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Long-form videos overwhelm teams trying to cut engaging shorts with accurate captions and consistent formatting. This skill provides an end-to-end, production-ready approach to automate clipping, transcription, captioning, and formatting for social distribution.

Core Features & Use Cases

  • End-to-end workflow for turning long videos into shareable shorts with burned-in captions
  • Download, transcribe, select viral segments, generate SRT captions, crop to vertical, and prepare thumbnails
  • Use case: a creator turns a 60-minute talk into 4x 30–60s shorts for YouTube Shorts, TikTok, and Instagram Reels

Quick Start

Start by downloading a long video with yt-dlp, transcribe it, identify 3–5 viral segments, and generate 9:16 clips with burned 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 automate turning long-form videos into vertical shorts with burned-in captions?

You can automate video clipping by using yt-dlp to download long-form content, whisper for transcription to generate SRT files, and ffmpeg to crop to 9:16 vertical formats and burn in captions. This end-to-end protocol handles ingestion through final clip preparation.

What is the best way to generate SRT captions for YouTube Shorts from a full-length video?

The best way to generate SRT captions is by applying a speech-to-text tool like whisper to the downloaded video file. This produces an SRT file that ffmpeg uses to burn accurate captions directly into your vertical shorts.

Can I use yt-dlp and ffmpeg together to crop and format viral clips for TikTok and Instagram Reels?

Yes, yt-dlp downloads the source video and ffmpeg processes it to crop vertical 9:16 formats and burn in captions. This combination effectively produces shareable shorts tailored for platforms like TikTok and Instagram Reels.

Does this automated video clipping workflow handle thumbnails and error handling for content pipelines?

Yes, the automated clipping workflow includes error handling and asset generation. It produces not only the cropped clips and SRT captions but also generates thumbnails, providing a production-ready pipeline from video ingestion to optional publishing hooks.

How do I select viral segments from a 60-minute talk before generating shorts?

You select viral segments by first downloading the long video and transcribing it with an STT tool. You then analyze the transcript to identify 3-5 high-engagement segments before using ffmpeg to generate the 30-60s vertical clips.