create-video

Generate videos from natural language prompts with configurable duration, orientation, and avatar.

1|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/shige1014-dev/backup-OpenMontage --skill create-video-shige1014-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-video
Source: https://github.com/shige1014-dev/backup-OpenMontage/tree/main/.agents/skills/create-video
Command: npx skills add https://github.com/shige1014-dev/backup-OpenMontage --skill create-video-shige1014-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Generate complete videos from simple natural language prompts so users can produce prototypes, demos, explainers, or marketing clips without designing scenes, selecting avatars, or writing detailed timelines manually.

Core Features & Use Cases

  • One-shot Prompt-to-Video: Describe the concept and let the Video Agent handle script, avatar selection, visuals, pacing, voiceover, and captions.
  • Asset Support & Polling: Upload reference images, audio, or video assets and poll for completion or use webhooks for async notification.
  • Use Case: Quickly produce a 60–90 second product demo or social clip by providing a production-style prompt and optional config for duration, orientation, or avatar lock.

Quick Start

Create a 60-second product demo video showcasing our new calendar app, professional tone, and energetic pacing by describing the concept in one prompt.

Frequently Asked Questions about create-video

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

FAQPage Schema
How do I generate a video from a text prompt without specifying scenes or avatars?

You can generate a finished video from a single natural language prompt by letting the Video Agent automatically handle script creation, avatar selection, visuals, pacing, voiceover, and captions.

Can I use HeyGen Video Agent to create a 60-second product demo from one prompt?

Yes, you can produce a 60 to 90 second product demo or marketing clip by providing a production-style prompt and optional config inputs like duration_sec, orientation, or avatar_id.

How does asynchronous video generation handle completion and status checks?

Asynchronous video generation supports polling for completion status or using webhooks for async notification, allowing you to retrieve finished videos once the rendering process is done.

Can I upload my own reference images and audio assets for prompt-to-video generation?

Yes, asset support allows you to upload reference images, audio, or video assets alongside your natural language prompt to guide the final video generation output.

Do I need to manually configure voiceover and pacing for explainer videos?

No, the Video Agent automatically handles voiceover and pacing for explainer videos based on your natural language prompt, eliminating the need for manual timeline editing or scene design.

What are the limitations of using one-shot prompt-to-video generation?

One-shot prompt-to-video generation is designed for quick prototypes, demos, and marketing clips, and may not support highly specific scene pre-specifications or complex manual timeline adjustments.