Short clips from long videos
/shorts
/shorts is a Claude Code skill in the Video & Motion section. It is maintained by AgriciDaniel and published under the MIT license. Pulls the best vertical clips out of a long video: transcribes, proposes segments, adds animated captions and exports for Shorts, TikTok and Reels.
Author's description
Interactive longform-to-shortform video creator. Extracts viral-ready short clips from long videos using Claude as the orchestrator. Transcribes with faster-whisper (GPU), Claude scores and presents candidate segments interactively, user picks and adjusts, Remotion renders premium animated captions (Bold/Bounce/Clean styles), FFmpeg exports platform-optimized files (YouTube Shorts, TikTok, Instagram Reels). Use when user says "shorts", "short clips", "shortform", "extract clips", "tiktok from video", "reels from video", "vertical clips", or "create shorts".
Use it when
- You have a long video or podcast and want short clips from it
- You want to pick segments yourself from scored candidates
- You need vertical exports for YouTube Shorts, TikTok and Instagram Reels
Not for
- Editing the long video itself
- Running unattended: the process is interactive and asks for your approval
What you get
Vertical 1080x1920 MP4 files with animated captions, exported in variants for YouTube, TikTok and Instagram Reels.
How to ask for it
Pull viral short clips from this long video for TikTokTurn this interview into several Reels with animated captionsI need vertical clips from this video for YouTube Shorts
Install
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bashAfter installing with the script, type /shorts. Using Cursor, Windsurf or Codex? Platform guides
Questions about this skill
- Do I choose the clips?
- Yes. Claude scores and presents candidate segments, and you pick and adjust which ones get rendered.
- Which platforms does it cover?
- YouTube Shorts, TikTok and Instagram Reels, exported for a single platform or all three.
- Does it need a GPU?
- It transcribes with GPU-accelerated faster-whisper and detects your GPU up front; if GPU encoding fails, the skill suggests falling back to CPU.
Demo coming soon