grok-video

Generate AI videos from text or reference images via xAI Grok Imagine Video.

Updated May 25, 2026
One-click install
npx skills add https://github.com/fuyucn/skills --skill grok-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grok-video
Source: https://github.com/fuyucn/skills/tree/main/grok-video
Command: npx skills add https://github.com/fuyucn/skills --skill grok-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg-static, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill streamlines the complex process of generating high-quality AI videos by automating the workflow from prompt engineering and API interaction to post-generation review.

Core Features & Use Cases

  • Full Pipeline Automation: Handles text-to-video and reference-image-to-video generation, including polling, downloading, and metadata tracking.
  • Quality Control: Provides a built-in contact sheet generator for rapid visual inspection of motion, identity consistency, and potential artifacts.
  • Use Case: A content creator can use this to generate a 10-second cinematic clip from a reference image, automatically save the output, and immediately review a contact sheet to ensure the subject's identity remains consistent before finalizing the asset.

Quick Start

Run the grok-video script with a prompt and your desired duration to generate a video and save it to your local output directory.

Frequently Asked Questions about grok-video

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

FAQPage Schema
How do I automate AI video generation using the xAI Grok Imagine model?

You can automate AI video generation with a CLI-based workflow that handles text-to-video and reference-image-to-video tasks, processing polling, downloading, and metadata tracking automatically through the xAI Grok Imagine Video model.

Can I generate a video from a reference image and keep the subject identity consistent?

Yes, reference-image-to-video generation is supported. The workflow includes a built-in contact sheet generator to rapidly inspect frames for motion, identity consistency, and visual artifacts before finalizing the output.

How do I review AI video artifacts and motion quality after generation?

You review AI video quality using an integrated frame-based contact sheet generator. It extracts frames from the downloaded video, allowing you to rapidly visually inspect motion consistency and potential artifacts.

Do I need an xAI API key and Node.js to run the AI video generation script?

Yes, you need an active xAI API key and a Node.js environment to execute the generation and review scripts. The ffmpeg-static dependency is also required for video processing and frame extraction.

What is the best way to manage text-to-video polling and downloading via CLI?

The best way to manage text-to-video polling and downloading is using an automated CLI script that handles the full pipeline, from sending the prompt to the xAI API and polling for status, to downloading the final video asset with metadata tracking.