growthub-video-generation

Bind local reference images as typed data URLs for Veo and Vertex video generation.

48|12|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/Growthub-ai/growthub-local --skill growthub-video-generation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: growthub-video-generation
Source: https://github.com/Growthub-ai/growthub-local/tree/main/.claude/skills/growthub-video-generation
Command: npx skills add https://github.com/Growthub-ai/growthub-local --skill growthub-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Bind a local reference image as a typed data URL to the video-generation node to ensure correct reference-image bindings and avoid URL-only references.

Core Features & Use Cases

  • Enforces typed data URL bindings for reference images (refs[].dataUrl) to ensure compatibility with Veo / Vertex workflows.
  • Supports end-to-end video generation requests via a unified inputs model and hosted pipeline execution.
  • Facilitates safe, provider-agnostic video workflows by routing execution through growthub-pipeline-execute rather than raw fetch.

Quick Start

Provide a video prompt and a local reference image, and the system converts it to a typed data URL and runs the video-generation node.

Frequently Asked Questions about growthub-video-generation

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

FAQPage Schema
How do I bind a local reference image for Veo video generation?

To bind a local reference image for Veo video generation, convert the image to a typed data URL and attach it to the video-generation node using the refs[].dataUrl property, ensuring correct reference-image bindings and avoiding URL-only references.

Why does my video generation workflow fail with a URL-only reference image?

Video generation workflows fail with URL-only references because the pipeline requires typed data URL bindings to correctly process the image. You must use refs[].dataUrl to validate inputs and ensure compatibility with Veo and Vertex providers.

What is the best way to run video generation across different pipelines?

The best way to run video generation across pipelines is routing execution through a unified inputs model and hosted pipeline execution rather than raw fetch, which facilitates safe, provider-agnostic video workflows for Veo and Vertex.

Do I need to use raw fetch to generate videos with Vertex providers?

No, you do not need to use raw fetch to generate videos with Vertex providers. You should route execution through the growthub-pipeline-execute node to ensure safe, provider-agnostic video workflows and proper input validation.

Can I use a single inputs model for different video generation providers?

Yes, you can use a single inputs model for different video generation providers. This approach supports end-to-end video generation requests across Veo and Vertex workflows by validating inputs and enforcing typed data URL reference bindings.