indiesoftby

An example configuration of AGENTS.md and a set of skills for AI-assisted game development with the https://defold.com engine.

27
1
100% credibility
Found Feb 18, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A setup that equips AI coding assistants with knowledge of a game engine's structure and tools to help users create games through natural language requests.

How It Works

1
💡 Discover the game-making helper

You hear about a special setup that lets AI friends help build games in your favorite game tool.

2
📥 Grab your game project

Start or open a simple game project in the Defold editor, ready for adventure.

3
Add the AI magic files

Copy a few helpful files into your game's main folder, connecting your AI buddy to your project.

4
🤖 Wake up your AI assistant

Tell your AI chat tool to prepare by downloading game pieces and learning your project's ways.

5
🎮 Chat to create your game

Describe what you want in plain words—like 'add a jumping player'—and watch the AI build screens, characters, and movements.

6
▶️ Test and tweak

Run your game, see it come alive, and ask the AI to fix or add more fun features.

🏆 Your game is ready!

Celebrate as your fully playable game bursts to life, all built with easy AI chats.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 27 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is defold-agent-config?

This GitHub repository provides a plug-and-play example configuration for AI agents in Defold game projects, including an AGENTS.md file and Python-based skills folder. Drop the files into your Defold project root, tweak for your AI tool like Cursor or GitHub Copilot, and prompt naturally: "Add a player with sprite and collision" or "Build and run the game." It equips agents with Defold API knowledge, dependency fetching, proto file editing for shapes, and screen scaffolding, acting as an example configuration yaml home assistant for agent-driven workflows or example github workflow for game dev.

Why is it gaining traction?

In a sea of generic AI setups, this stands out with Defold-specific skills like auto-generating convex shapes from images, fetching engine docs/examples, and building via the editor—saving hours on boilerplate. Supports 10+ agents out-of-box with simple renames, plus best practices like one-task chats and planning first. Devs notice instant productivity: AI respects your project conventions, handles natives/C++, and updates deps from game.project.

Who should use this?

Defold game devs using Cursor, Copilot, or Claude Code who build 2D games/screens and hate manual proto tweaks or API lookups. Ideal for solo indies prototyping arcade games, adding Monarch screens/popups, or scripting physics—especially if you're tired of scrolling Defold forums mid-flow. Skip if you're not on Defold 1.12+ with Python 3.11.

Verdict

Grab it if you're a Defold dev eyeing AI boosts—solid example github repository despite 15 stars and 1.0% credibility score signaling early maturity. Polish docs and community skills to production-ready; for now, perfect research starter for agent configs.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.