short-form-video

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

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/chriswestt/claude-skills --skill short-form-video-chriswestt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: short-form-video
Source: https://github.com/chriswestt/claude-skills/tree/main/short-form-video
Command: npx skills add https://github.com/chriswestt/claude-skills --skill short-form-video-chriswestt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Short-form vertical video production is complex and time-consuming, requiring choreography, timing, captions, and consistent reference frameworks. This skill consolidates the May Shorts 19 playbook into a repeatable pipeline that yields 9:16 videos with face motion, synced overlays, and karaoke captions.

Core Features & Use Cases

  • Audio-first workflow with scene-boundary decisions and data-driven timing.
  • Four-layer composition scaffold (ambient background, face wrapper, seam treatment, captions) ensuring deterministic renders.
  • Automatic captioning alignment and face-mode choreography across 1080x1920 outputs for platforms like TikTok, Reels, and Shorts.

Quick Start

Invoke the short-form-video skill inside the Hyperframes workflow to begin building a 1080x1920 talking-head short with synced scenes and karaoke captions.

Frequently Asked Questions about short-form-video

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

FAQPage Schema
How do I automate short-form vertical video creation with face motion and synced captions?

Automate short-form vertical video creation by invoking the short-form-video skill inside Hyperframes to generate 1080x1920 talking-head clips with face-mode choreography, synced scene overlays, and karaoke captions.

What is the best way to ensure deterministic rendering for 1080x1920 talking-head videos?

Ensure deterministic rendering for 1080x1920 talking-head videos by using a strict four-layer composition scaffold that separates the ambient background, face wrapper, seam treatment, and captions.

Can I use Hyperframes to add karaoke captions to vertical videos for TikTok and Reels?

Yes, you can use Hyperframes to add karaoke captions to vertical videos. The workflow applies an audio-first pipeline with data-driven timing to align caption styling automatically for platforms like TikTok and Reels.

Does the vertical video workflow support scene-boundary timing and overlay synchronization?

Yes, the vertical video workflow supports scene-boundary timing and overlay synchronization through an audio-first workflow that drives data-driven timing decisions and applies face-mode choreography across synced scene overlays.

Why use a four-layer composition scaffold for short-form video production?

Use a four-layer composition scaffold for short-form video production to consolidate complex choreography and timing into a repeatable pipeline, ensuring consistent reference frameworks and strict timing across all 1080x1920 outputs.

Do I need Hyperframes to generate 9:16 videos with face-mode choreography?

Yes, you need Hyperframes to generate 9:16 videos with face-mode choreography, as the skill automates the end-to-end creation pipeline directly inside the Hyperframes workflow environment.