Opengame Agentic Game Creation

This is a complete framework for generating playable web games from text prompts, not just a code snippet generator. It combines a template library that scaffolds stable architectures, a debug skill that applies verified fixes across iterations, and OpenGame-Bench for automated evaluation via headless browser testing. You get HTML/JS/CSS games out, and it works with any OpenAI-compatible LLM backend including their custom GameCoder-27B model. The interesting bit is how it treats both templates and debug protocols as living knowledge bases that grow over time, so successful patterns get reused systematically. If you need throwaway game prototypes or want to explore agentic code generation with real evaluation metrics, this gives you the full pipeline.

skills.sh installs: 268
GitHub stars: 26
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill opengame-agentic-game-creation --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenGame: Agentic Web Game Creation

Skill by ara.so — Daily 2026 Skills collection.

OpenGame is an open-source TypeScript framework that generates fully playable web games end-to-end from a single natural language prompt. It combines Game Skill (Template Skill + Debug Skill), an optional specialized GameCoder-27B LLM, and OpenGame-Bench for automated evaluation across Build Health, Visual Usability, and Intent Alignment.

What OpenGame Does

Takes a high-level game design prompt and produces a runnable browser game (HTML/JS/CSS)
Template Skill: Maintains a growing library of project skeletons to scaffold stable architectures
Debug Skill: Keeps a living protocol of verified fixes to repair cross-file integration errors systematically
OpenGame-Bench: Evaluates generated games via headless browser execution + VLM judging across 150 diverse prompts
Supports any OpenAI-compatible LLM backend (GPT-4o, Claude, GameCoder-27B, etc.)