Back to directory

GodotPrompter

An agentic skills framework for Godot 4 game development that gives AI coding agents structured, version-specific knowledge of GDScript, C# and engine subsystems instead of generic advice.

GodotPrompter

GodotPrompter is a plugin of structured domain-knowledge skills for Godot 4.x game development, loaded on demand by AI coding agents such as Claude Code, GitHub Copilot, Antigravity and Cursor. When asked to add a feature such as a state machine or multiplayer support, the agent loads the matching skill and follows Godot-specific conventions instead of relying on generic training knowledge.

It ships 56 skills covering project setup, architecture, gameplay systems, input handling, physics, 2D and 3D systems, animation, shaders, audio, UI, multiplayer, localization, procedural generation, XR and VR, native extensions, multithreading, mobile shipping, optimization, GDScript and C# patterns, a teaching mode, and several third-party addons, targeting Godot 4.3 and newer with additional annotated sections for newer engine releases. It builds on the underlying skill-loading and workflow infrastructure of the Superpowers plugin for Claude Code.

It installs as a Claude Code plugin through a marketplace command or from a local clone.

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.