muapi-youtube-shorts

Generates ranked vertical short clips from long-form videos via muapi.ai's AI clipping endpoint.

4.2k|481|Updated May 25, 2023
One-click install
npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-youtube-shorts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: muapi-youtube-shorts
Source: https://github.com/SamurAIGPT/Generative-Media-Skills/tree/main/.opencode/skills/muapi-youtube-shorts
Command: npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-youtube-shorts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Turning a long-form video into platform-ready YouTube Shorts, TikTok, or Reels clips normally requires manual transcription, highlight hunting, and vertical cropping. This Skill automates that entire pipeline by delegating highlight extraction, deduplication, and face-tracked 9:16 cropping to muapi.ai's managed /ai-clipping endpoint.

Core Features & Use Cases

  • Platform-aware presets: Pass --platform shorts, tiktok, reels, or feed to automatically apply the right aspect ratio (9:16 or 1:1) and default clip count.
  • Ranked highlight extraction: Each returned clip includes a virality score (0-100), hook sentence, time range, and a reason explaining why the moment works.
  • Zero local tooling: Transcription, ranking, and cropping run server-side, so no ffmpeg, Whisper, or local LLM keys are needed.
  • Use Case: A podcaster pastes a YouTube URL and receives five ranked vertical clips with hooks and scores, ready to post to TikTok without opening a video editor.

Quick Start

Ask the agent to generate YouTube Shorts from a given video URL using the muapi-youtube-shorts skill with the shorts platform preset.

Frequently Asked Questions about muapi-youtube-shorts

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

FAQPage Schema
How do I turn a long YouTube video into Shorts automatically?

Run the run-youtube-shorts.sh script with --source set to your YouTube URL and --platform shorts. The skill calls muapi.ai's /ai-clipping endpoint, which transcribes the video, ranks highlights, and returns vertical 9:16 clips with scores and hooks.

What aspect ratios and clip counts does each platform preset use?

Shorts, TikTok, and Reels presets use 9:16 aspect ratio, with 3 default clips for Shorts and Reels and 5 for TikTok. The feed preset uses 1:1 with 3 clips. Any default can be overridden with --aspect-ratio or --num-clips.

Do I need ffmpeg or Whisper installed to generate short clips?

No local media tooling is required. Transcription, highlight ranking, deduplication, and face-tracked cropping all run server-side on muapi.ai. You only need muapi-cli installed and a valid MUAPI_API_KEY configured.

When should I use AI Clipping directly instead of this skill?

Use the underlying AI Clipping skill when you need full control over aspect ratio and clip count, want raw timestamps via --coords-only, or are integrating clipping into a custom renderer. This skill is for platform-tuned defaults.

Why did the API return fewer clips than I requested?

The source video contained fewer rankable highlights than the requested count. The endpoint dedupes overlapping candidates by score, so return the surviving clips rather than padding with low-score filler.