Generative-Media-Skills and ai-video-skill
These are complementary tools that address different stages of AI video generation: one provides foundational multi-modal generation capabilities (image, video, audio) via muapi.ai, while the other wraps those capabilities into a specialized skill for Claude/Cursor agents focused specifically on social media video creation with preset voices and styles.
About Generative-Media-Skills
SamurAIGPT/Generative-Media-Skills
Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.
Schema-driven CLI primitives delegate all operations to `muapi-cli`, enabling agents to generate across 100+ models (Midjourney, Flux, Kling, Veo3) with structured JSON outputs and semantic exit codes for agentic pipelines. The Expert Library layer adds domain-specific skills (Cinema Director for cinematography, Nano-Banana for reasoning-driven imagery, UI Designer for atomic design) that translate creative intent into technical directives. Runs as an MCP server exposing 19 typed tools to Claude Desktop, Cursor, and other MCP-compatible agents, with native support for async polling, local file upload, and direct media display via `--view`.
About ai-video-skill
aituberapp/ai-video-skill
AI video creation skill for Claude Code, Cursor, and AI coding agents. Create YouTube Shorts, TikTok, Instagram Reels, and long-form videos with 1,300+ voices and 27+ visual styles.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work