Claude Code skills that build complete Godot games
I’ve been working on this for about a year through four major rewrites. Godogen is a pipeline that takes a text prompt, designs the architecture, generates 2D/3D assets, writes the GDScript, and tests it visually. The output is a complete, playable Godot 4 project. Getting LLMs to reliably generate functional games required solving three specific engineering bottlenecks: 1. The Training Data Scarcity: LLMs barely know GDScript. It has ~850 classes and a Python-like syntax that will happily let a model hallucinate Python idioms that fail to compile. To fix this, I built a custom reference system: a hand-written language spec, full API docs converted from Godot's XML source, and a quirks database for engine behaviors you can't learn from docs alone. Because 850 classes blow up the context window, the agent lazy-loads only the specific APIs it needs at runtime. 2. The Build-Time vs. Runtime State: Scenes are generated by headless scripts that build the node graph in memory and serialize it to .tscn files. This avoids the fragility of hand-editing Godot's serialization format. But it means certain engine features (like `@onready` or signal connections) aren't available at build time—they only exist when the game actually runs. Teaching the model which APIs are available at which phase — and that every node needs its owner set correctly or it silently vanishes on save — took careful prompting but paid off. 3. The Evaluation Loop: A coding agent is inherently biased toward its own output. To stop it from cheating, a separate Gemini Flash agent acts as visual QA. It sees only the rendered screenshots from the running engine—no code—and compares them against a generated reference image. It catches the visual bugs text analysis misses: z-fighting, floating objects, physics explosions, and grid-like placements that should be organic. Architecturally, it runs as two Claude Code skills: an orchestrator that plans the pipeline, and a task executor that implements each piece in a `context: fork` window so mistakes and state don't accumulate. Everything is open source: https://github.com/htdt/godogen Demo video (real games, not cherry-picked screenshots): https://youtu.be/eUz19GROIpY Blog post with the full story (all the wrong turns) coming soon. Happy to answer questions.
- Agent IA
- Automatisation des Flux de Travail
- Génération de Code
✨ Résumé IA
Godogen is an open-source pipeline that uses Claude Code skills to generate complete, playable Godot 4 game projects from text prompts. It addresses LLM limitations in GDScript by using a custom reference system and employs a visual QA agent for testing.
Idéal pour
Indie game developers, Game development hobbyists, Prototyping game ideas
Pourquoi c'est important
Automates the creation of functional Godot 4 games from text prompts by overcoming LLM training data scarcity and integrating visual testing.
Fonctionnalités clés
- Generates complete, playable Godot 4 game projects from text prompts.
- Designs game architecture and writes GDScript code.
- Creates 2D and 3D game assets.
- Employs a custom reference system for GDScript to overcome training data scarcity.
Cas d'usage
- A solo indie game developer can use Godogen to quickly prototype game mechanics by providing a text prompt, allowing them to iterate on ideas without writing extensive boilerplate code.
- A game design student can leverage Godogen to generate functional game prototypes for class projects, focusing on learning game design principles rather than complex programming.
- A small game studio can utilize Godogen to rapidly generate initial game assets and scripts for a new project, speeding up the pre-production phase and allowing artists and designers to focus on higher-level tasks.