video-gen

Automates AI video generation with Veo and Sora models from text prompts.

Updated Jan 24, 2026
One-click install
npx skills add https://github.com/maxgent-ai/maxgent-plugin --skill video-gen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-gen
Source: https://github.com/maxgent-ai/maxgent-plugin/tree/main/skills/video-gen
Command: npx skills add https://github.com/maxgent-ai/maxgent-plugin --skill video-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI video generation from text prompts often requires multiple steps and manual setup. This Skill streamlines the workflow end-to-end, covering model selection, size/duration configuration, and delivery of the final video.

Core Features & Use Cases

  • End-to-end AI video generation with Veo and Sora models.
  • Flexible prompts, resolutions, and durations, including optional image prompts for Sora.
  • Automated workflow: environment check, task creation, status polling, and download.

Quick Start

Run the video-gen script with your chosen model, prompt, size, and duration, then retrieve the resulting video from the output directory.

Frequently Asked Questions about video-gen

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

FAQPage Schema
How do I automate AI video generation from text prompts using Veo or Sora?

AI video generation from text prompts is automated end-to-end by handling model selection, task creation, progress polling, and final video download for Veo and Sora models.

Can I use an image prompt with Sora for AI video generation?

Sora AI video generation supports optional image prompts, allowing you to provide a reference image alongside text prompts, resolution, and duration configurations to produce clips.

Do I need an API key to generate AI videos with Veo and Sora?

Generating AI videos with Veo and Sora requires the MAX_API_KEY environment variable to initialize and authenticate the automated task creation and polling workflow.

What's the best way to configure resolution and duration for text-to-video clips?

Text-to-video clip generation accepts flexible size and duration variants, allowing you to specify desired resolution and length parameters before task creation and automated polling.

How does the automated workflow handle video task polling and downloading?

The automated workflow handles video task polling by continuously checking generation status and automatically downloading the completed clip to an output directory once the task finishes.