Ai Video Generation

This one's for working with AI video generation APIs like Runway, Pika, and Stable Video Diffusion. You get actual client implementations with proper polling logic for async generation, not just curl examples. The Runway integration handles the full flow from submission to waiting for render completion with timeouts. There's a decent prompt engineering system that separates subject, action, camera movement, and lighting into structured objects instead of freeform strings. Also includes local generation with Stable Video Diffusion if you want to run it yourself. The code is production-ready with dataclasses and error handling, which is rare for AI API wrappers.

skills.sh installs: 162
GitHub stars: 2
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mindmorass/reflex --skill ai-video-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Video Generation Patterns

Best practices for generating videos with AI tools.

Platform Overview

Platform	Type	Strengths
Sora	Text-to-Video	Photorealistic, long-form
Runway Gen-3	Text/Image-to-Video	Fast, good motion
Pika Labs	Text/Image-to-Video	Stylized, accessible
Kling AI	Text-to-Video	Long duration, realistic
Luma Dream Machine	Text/Image-to-Video	Coherent motion
Stable Video Diffusion	Image-to-Video	Open source

Runway API Integration

import requests
from dataclasses import dataclass
from typing import Optional
import time

@dataclass
class GenerationRequest:
    prompt: str
    image_url: Optional[str] = None
    duration: int = 4  # seconds
    aspect_ratio: str = "16:9"
    motion_strength: int = 5  # 1-10

@dataclass
class GenerationResult:
    id: str
    status: str
    video_url: Optional[str] = None
    thumbnail_url: Optional[str] = None

SKILL.md on GitHub