Muapi Ai Clipping

Turns a long video URL into ranked vertical clips ready for TikTok, Reels, or Shorts. Each clip comes with a viral score, a hook line, and a reason why it might work, plus a hosted mp4. It's built on muapi.ai's clipping API and handles face tracking and cropping to 9:16, 1:1, or 4:5 without needing ffmpeg on your machine. If you're repurposing podcasts, interviews, or streams into social content, this saves you from manually scrubbing through footage. The viral scoring is obviously subjective, but having timestamps and reasoning attached to each clip is a solid starting point. Pass a coords-only flag if you just want the highlight ranges and plan to render yourself.

skills.sh installs: 2K
GitHub stars: 4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add samuraigpt/generative-media-skills --skill muapi-ai-clipping --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Clipping

One API call: long video in → ranked vertical short clips out.

Each clip ships with a viral score (0–100), an opening hook line, a one-sentence "why it works" reason, and a hosted mp4 URL.

Underlying API: https://muapi.ai/playground/ai-clipping Reference implementation (open source): https://github.com/SamurAIGPT/AI-Youtube-Shorts-Generator

When to Use

Auto-clip a podcast, interview, lecture, vlog, or stream into TikTok / Reels / Shorts.
Extract the best 30–75s moments from any hosted video URL.
Get face-tracked vertical (9:16), square (1:1), or portrait (4:5) crops without running ffmpeg locally.

If you only need raw timestamps for your own renderer, set --coords-only to skip cropping and just get the highlight ranges.