ai-video-gen

Name: ai-video-gen
Availability: InStock
Author: gyalamanch001a

Generates AI videos from text prompts and reference images via selectable providers.

Updated Apr 2, 2026

Search Tags:#video generation #multi-provider #prompting #cinematic #text-to-video #image-to-video #social content

Ready to run

npx skills add https://github.com/gyalamanch001a/pur-new --skill ai-video-gen-gyalamanch001a

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ai-video-gen
Source: https://github.com/gyalamanch001a/pur-new/tree/main/.agents/skills/ai-video-gen
Command: npx skills add https://github.com/gyalamanch001a/pur-new --skill ai-video-gen-gyalamanch001a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of turning ideas, images, and brief prompts into finished AI-generated videos, helping creators produce polished clips without managing multiple video tools manually.

Core Features & Use Cases

Text-to-Video Generation: Turn written prompts into cinematic clips with selectable providers and aspect ratios.
Image-to-Video Creation: Animate reference images into dynamic video sequences for products, scenes, or social content.
Provider Comparison and Fallback: Choose among VEO, Kling, Sora, Runway, Seedance, MiniMax, and LTX options through gateway-aware routing.
Use Case: A marketer can generate a vertical social ad from a product photo, while a creator can test several models to balance speed, quality, and cost.

Quick Start

Ask the Skill to generate a cinematic 16:9 video from your prompt and, if needed, include a reference image and preferred provider.

Frequently Asked Questions about ai-video-gen

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

FAQPage Schema

How do I generate AI video from text prompts and reference images?▼

To generate AI video from prompts, you provide a text description or a reference image, select a video provider, and set an aspect ratio. The Skill routes your request through authenticated gateways to produce cinematic clips.

Can I create image-to-video animations for social content?▼

Yes, you can animate reference images into dynamic video sequences for social content. The Skill uses image-to-video creation to transform static product photos or scene images into vertical or horizontal video formats.

What's the best way to compare text-to-video models like VEO, Kling, and Sora?▼

The best way to compare text-to-video models is using the provider comparison feature. You can generate clips across VEO, Kling, Sora, Runway, Seedance, and MiniMax to balance speed, quality, and cost for your specific video generation needs.

Do I need authenticated access to use multi-provider video generation?▼

Yes, you need authenticated access through HeyGen or fal.ai gateways to use multi-provider video generation. These gateways handle the routing to your selected provider and manage the asynchronous polling required for video completion.

How does asynchronous polling work for AI video generation?▼

Asynchronous polling for AI video generation works by continuously checking the gateway for completion status after you submit a prompt. Because cinematic video rendering takes time, the Skill polls the provider until your final video clip is ready.

Are there limitations when choosing aspect ratios for cinematic clips?▼

The main limitation when choosing aspect ratios for cinematic clips is provider support. While the Skill offers aspect-ratio control, you must ensure your selected provider supports the specific dimensions required for your social content or cinematic format.