Back to directory

Scenario Agent Skills

A library of Agent Skills that teach AI coding agents to generate production-ready images, video, audio, textures and 3D assets through the Scenario MCP server, plus specialist skill teams that drive Blender, Maya, ZBrush and Unreal Engine.

Scenario Agent Skills

Scenario Agent Skills is a collection of Agent Skills-format instructions that let AI coding agents such as Claude Code, Cursor, Codex and Copilot generate production-ready creative content through the Scenario MCP server: images, video, audio, textures, skyboxes, 3D assets and custom-trained models, for games, entertainment and other creative work.

Skills are grouped by role and by outcome, covering areas such as game art and environments, marketing and brand visuals, video and audio production, consistent characters and custom model training, and image generation and editing, with an install command for each group.

A separate set of expert-tool skill families drives digital content creation software and game engines already installed on the user's machine, including ZBrush, Blender, Maya, Unreal Engine and Unity; these are distilled from tutorials and documentation and need the target application rather than the Scenario MCP server.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.