skills.rest
scanbott
scanbottCOMMUNITY
Explore all skills by this author →
GitHub

short-form-video

Creates 9:16 videos with Hyperframes, syncing scenes, captions, and choreography.

Updated Apr 21, 2026
Search Tags:#timing#video-editing#short-form-video#vertical-video#hyperframes#karaoke-captions#face-mode
One-click install
npx skills add https://github.com/scanbott/claude-skills --skill short-form-video-scanbott
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: short-form-video
Source: https://github.com/scanbott/claude-skills/tree/main/short-form-video
Command: npx skills add https://github.com/scanbott/claude-skills --skill short-form-video-scanbott

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables rapid creation and iteration of short-form vertical videos (9:16) using the Hyperframes framework, encapsulating the May Shorts 19 playbook to ensure consistent face-driven choreography, caption-synced scenes, and a robust quality checklist.

Core Features & Use Cases

  • Four-layer composition scaffold: ambient-bg, face, seam-treatment, and scene overlays with karaoke captions.
  • Audio-first workflow: prioritize audio timing, transcribe and align scenes, and verify word-exact frames.
  • Use Case: produce a 10–30s TikTok/Reels/Shorts-style vertical video from a talking-head recording plus script, with synced captions and dynamic scene overlays.

Quick Start

Invoke the Hyperframes framework first and build a 1080x1920 short-form video using the May Shorts 19 playbook.

Frequently Asked Questions about short-form-video

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

FAQPage Schema
How do I create vertical short-form videos with synced karaoke captions?▼

You can build 9:16 short-form vertical videos using a four-layer composition scaffold of ambient-bg, face, seam-treatment, and scene overlays to produce TikTok/Reels/Shorts-style posts with dynamic karaoke captions.

What is the best way to sync scene timing in a TikTok talking-head video?▼

The best way to sync scene timing in a TikTok talking-head video is an audio-first workflow: prioritize audio timing, transcribe the recording, align scenes to the script, and verify word-exact frames for deterministic rendering.

How do I add face-mode choreography to a 9:16 vertical video?▼

To add face-mode choreography to a 9:16 vertical video, apply the May Shorts 19 playbook within the Hyperframes framework, isolating the face layer in a four-layer composition scaffold for consistent dynamic movement.

Do I need the Hyperframes framework to build 9:16 short-form vertical videos?▼

Yes, you must invoke the Hyperframes framework first to build 1080x1920 short-form vertical videos, as it provides the prescribed composition scaffold and word-exact frame verification workflow required for deterministic renders.

Can I produce a 10 to 30 second Reels video from a script and a recording?▼

Yes, you can produce a 10–30 second Reels video from a talking-head recording and a script by applying retiming, caption synchronization, and dynamic scene overlays to create the final vertical video.

Related Skills

Explore More Design & Creative Skills→
hoanghd218hoanghd218
3

short-form-video

Create 1080x1920 vertical videos with talking-head footage, motion graphics, and synchronized captions.

Community
Advanced
het8802het8802
3

instagram-reels

Generate scripts, voiceovers, and visuals for short-form videos.

Community
Advanced
maxgent-aimaxgent-ai

audio-transcribe

Transcribe audio and video files with word-level timestamps using WhisperX.

Official
Advanced
chriswesttchriswestt

short-form-video

Automate 1080x1920 talking-head video creation with Hyperframes, overlays, and karaoke captions.

Community
Advanced