How I'd use Unity + Claude Code to vibe code a game

Background: I've been making games and apps with Unity for 16+ years.

I had someone ask a question about how to use Claude Code to make a game and after writing a short novel, I thought, "hey, this could be helpful to others" -- but I'll let y'all be the judge.

(note: a lot of this would also apply to making an app or any piece of software with Claude Code)

Someone asked me about making something based off an existing game, but also how would he attract programmers to help him / work for him. Below is my response:

---

To start... you need Unity (and some basic familiarity with it) and the Unity MCP and Claude Code (the CLI) -- and claude opus. Opus is extremely good at letting you drop the whole vision at once (including screenshots) and tell it what you're wanting to do. In this case, make a game like XYZ. And it'll tell you where to start and how to progress from there.

The one thing that AI cannot do is make a game that's fun. Not intentionally, anyway. It's pretty much always going to need tweaks.

In your case, wanting to make a game with big monster trucks... The key to ANY game is usually going to be one core piece or mechanic. I would tackle that hardest piece first. You need to get those vehicles rolling and feeling good to play. AI can build something, and it can build something you can tweak, but it cannot "make a fun game" any more than AI can "make a song that moves me" -- it's too subjective to the person interacting.

Talk to Claude Opus, tell it the grand plans, ask it where to start, ask it to build a tech spec for the v0.1 -- again, I'd absolutely start with the car. Tell it you're going to use claude code and the unity mcp. It can build a markdown file very specifically for claude code, along with instructions. Then go to a directory with that file in it (probably needs to be an existing but empty Unity project if you're going to use Unity), go into claude's CLI and reference that file with @ saying something like, "I want you to plan out and then build to the specification in the @car_game.md file" (and the @ will bring up a list of files, fyi)

It might seem like an extra step to go through Opus, but I promise you will get so, so, so much further doing it that way.

ALL the other stuff... the driver and car customization and LITERALLY EVERYTHING ELSE does not matter if the key mechanic of the game is not fun. And only you can be the judge of that.

that's the hardest problem -- tackle it first, or you're just wasting time.

as for how to attract people to work with you... if you don't have money to pay them, you better have a grand vision. DO NOT show up in the game dev groups and promise rev share, because all the people in there have heard it 1,000,000 times and will laugh you out of the room. If anyone does take you up on that, they probably don't have the experience to do what you need.

...until you have something fun.

If you have something fun... that looks fun to play in a video... that is fun for you to play. . THEN you can go show it off and start recruiting artists and other people to help. if you promise rev share, you'll probably get laughed out of the room. if you promise you'll do your best and this is what you're bringing to the table, and look at this video, it's already fun, I know it's just simple shapes but it's really fun and here's a webGL demo over here... THEN you might start attracting the right kind of people you want to help you with it.

I don't have advice beyond that for finding people to work with you. The painful truth is that ideas are a dime a dozen (probably a lot more since AI) -- and they just don't matter. Especially now. It's all about the execution. Which is why the "idea guys" usually get laughed out of the room. (or are building it themselves these days)

beyond that... the people who can write the code and are really good at it.. already have more ideas of their own than they could ever possibly build. more unfinished projects. more ideas and offshoots and the people they've worked with have ideas -- and they're going to pick any of those way, way before they pick someone random who shows up and "has a great idea for a game and it's gonna make piles of money and we'll split the revenue" -- that is spoken like someone who has never, ever executed an idea and seen it to the finish, and those who have can identify it in about a second.

if you're bringing money to the table... that's entirely different. then you're not the idea guy, then you're the client. But most idea guys are just bringing an idea and wanting everyone to work on their idea for free, convinced that it's the best idea in the whole world.

Spoiler alert: it isn't.

Spoiler alert: even if it was.. it's all about the execution. The idea is a multiplier for the execution. You can take an okay idea and execute it *really, really well* and you've got something pretty amazing. Or you can take a KILLER idea, and execute it really badly... and you've got nothing but regret.

---

I'd love to hear if this was helpful to people in the group and happy to answer any questions about what I said or anything else.

3 comments