[eudamoniac]

I can't decide if this is impressive or not. At first I think it is, but also the best demos you could find were not good games, and likely not even good bases for further iteration. It seems pretty likely that this tool would increase the speed of shipping a salable game by zero minutes. So it's kind of impressive but at the same time not.

[tartoran]

If you put in the effort to polish the scenes, mechanics, and overall feel, then with a great idea and a few iterations, you could potentially build a sellable game. I honestly do not know what it takes to sell a game, but if you have a strong idea and want to put it online, a tool like this can take you surprisingly far and let you focus on the bigger-picture parts of the game.

I think it's quite impressive without even trying it. I think more and more tools like this will pop up soon.

[eudamoniac]

Well no, what I mean is I've used Godot a lot and I think it's likely that the effort to polish this output is more than the effort to start from scratch. Godot as a codebase is very easy to become horrendous spaghetti. Even though this is some form of a start, I kind of doubt it would decrease time to ship by any amount, maybe even increase time to ship, for the same reasons that greenfielding is faster and easier than incrementally refactoring a legacy clusterfuck written by juniors.

[tartoran]

You may be right, I don't have any experience with Godot but as a noob game dev it feels to me that if I have a good clear idea (perhaps a simple one), a Claude skills pipeline would help move things faster, get to something roughly working relatively easily. From there to a polished game there's considerable effort, I'm sure. Since I've had a pretty good experience with LLMs and making Lua games my inclination is to think this would propel me quite well with Godot as well. What do I know...