scenario-labs/skills

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

What it solves

This project provides a comprehensive set of "skills" that enable AI coding agents (such as Claude Code, Cursor, and Copilot) to generate production-ready creative content using the Scenario platform. It bridges the gap between LLM-based agents and professional creative workflows, allowing agents to handle tasks like image generation, video production, 3D asset creation, and custom model training without manual intervention.

How it works

The project implements the Agent Skills format, following the Model Context Protocol (MCP). It operates through the Scenario MCP server, which allows AI agents to call specific tools for different creative tasks. There are two primary categories of skills:

  1. Scenario MCP Skills: These are 65+ skills that connect to the Scenario cloud platform to generate images, video, audio, and 3D assets.
  2. Expert Tools: These are specialized skill sets that drive local Digital Content Creation (DCC) software and game engines (like Blender, Maya, Unreal Engine, and Unity) based on expert tutorials and documentation.

Who it’s for

Creative professionals, game developers, and marketing teams who use AI coding agents to automate the production of visual and audio assets for games, entertainment, and other creative verticals.

Highlights

  • Multimodal Generation: Supports images, video, audio, textures, skyboxes, and 3D meshes (GLB/FBX).
  • Production-Ready Workflows: Includes specialized skills for product photography, brand kits, storyboards, and sprite animations.
  • Game Engine Integration: Direct tools for game-ready assets like PBR materials and seamless textures.
  • Consistency Tools: Features for maintaining character, product, or style consistency across multiple assets through identity libraries and custom model training.
  • Crossover with DCC Tools: Ability to drive local professional software like ZBrush and Blender.

Related

  • Project
    xandergos/terrain-diffusion-mc

    A Minecraft Fabric mod that uses a diffusion model to generate highly diverse and realistic terrain and landscapes.

  • Project
    InternLM/Intern-S1

    A series of multimodal foundation models optimized for scientific intelligence and long-horizon agents, capable of reasoning across complex scientific domains like chemistry and biology.

  • Project
    OleksandrChekhovskyi/hax

    hax is a lightweight, terminal‑native AI coding assistant written in C. It talks to cloud or local LLM providers (OpenAI, Anthropic, llama.cpp, Ollama, etc.) via a simple REPL or one‑shot mode, streams Markdown‑formatted answers, and keeps a transparent transcript. Install via Homebrew, AUR, pre‑built binaries, or compile from source; it’s aimed at developers who want a fast, low‑resource, fully auditable AI tool that lives entirely in the terminal.

  • Project
    SkyworkAI/UniPic

    A unified multimodal model series for image editing, generation, and understanding, featuring high-speed multi-image editing and autoregressive modeling.