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.

What it solves

This project provides a comprehensive toolset for AI agents (such as Claude Code, Cursor, and Gemini CLI) to generate, edit, and display professional-grade images, videos, and audio. It bridges the gap between high-level creative intent and the technical API calls required to produce high-quality multimodal media using various AI models.

How it works

The system is built on a schema-driven architecture that leverages the muapi-cli to interact with over 100 AI models (including Midjourney, Flux, and Kling). It is organized into two main layers:

  • Core Primitives: Thin wrappers around the CLI for raw API access, handling tasks like file uploads, basic image editing, and authentication.
  • Expert Library: A collection of high-value "skills" that translate creative goals into technical directives. This includes specialized workflows for cinematography, UI design, and branding.

Additionally, it offers an MCP (Model Context Protocol) server, allowing agents to call 19 structured tools directly without needing to execute shell scripts.

Who it’s for

It is designed for developers and creators using AI agents to automate multimodal content creation, specifically those utilizing MCP-compatible tools like Claude Desktop or Cursor.

Highlights

  • Agent-Native Design: Uses structured JSON outputs and semantic exit codes for seamless integration into agentic pipelines.
  • Expert Knowledge Layer: Includes pre-built skills for professional film direction, atomic design for UI, and geometric primitives for logos.
  • Extensive Recipe Pack: Features 41 LLM-orchestrated workflow recipes, such as converting photos to 3D action figures or creating cinematic product ads.
  • Broad Model Support: One-click access to a wide array of models including Midjourney v7, Flux Kontext, Seedance 2.0, and Kling 3.0.
  • Direct Media Display: Includes a --view flag to automatically open generated media in the system viewer.

Related

  • Project
    yanhua1010/self-media-content-workflow

    A modular suite of AI agent skills for self-media content production, covering everything from trend research and strategy to platform-native copywriting and publishing.

  • Project
    0xsline/OpenChatCut

    An open-source, local-first AI video editor that combines a professional multitrack timeline with conversational agents for editable, agent-driven video production.

  • Project
    inference-sh/skills

    A collection of AI agent skills and SDKs that enable models to generate images, videos, search the web, and automate social media via the inference.sh CLI.

  • Project
    Haervwe/open-webui-tools

    A comprehensive collection of 20+ tools, function pipes, and filters for Open WebUI that adds academic research, multi-modal generation, and autonomous agent capabilities.