How bobaaa Used Opus 5.5 to Ship Skyhold to CrazyGames in 9 Days
Built by bobaaa · · Source: X
Result: According to bobaaa: 22 Opus passes, about $164, live on CrazyGames nine days after an empty folder, passing the SDK check 7 of 7 on the first try. First CrazyGames day: 141 impressions, 1.4% click rate, about 3 minutes of play, 0 crashes.
What they built
bobaaa built Skyhold, a browser game where houses float in under balloons and you drop each one onto a floating island. Every house tips the island, and if you lose five homes it flips. According to bobaaa, Opus 5.5 wrote every line of code and also made the art, the mascots and the music. They say it took 22 passes and about $164, and the game went live on CrazyGames nine days after starting from an empty folder.
How it works
The post walks through the process step by step, though the three full prompts are not included in the text.
- One rule first. The whole game comes from one sentence: the island has a centre of mass. bobaaa's test is that the rule fits in one line.
- A one-page doc. Before any code, Opus gets the rule, the loop, how you win and lose, the camera, the controls for desktop and phone, and what counts as done for the day. They say the first pass took 46 minutes and came back with a playable island.
- One system per pass. Each brief has five parts: files to read first, the one thing to do, what must keep working, a finish line they can check by playing, and no browser or runtime errors. Their most expensive pass was $12.94 and the cheapest was $1.01.
- No engine, no image files. three.js handles the 3D world and everything else is drawn in code, including two SVG mascots named Moss and Puff. The full build is 1.5 MB.
- Self-recorded trailers. A capture mode runs a scripted demo of the real game, and a headless browser records it frame by frame.
- Portal builds. One adapter hides each portal's SDK, and a build script makes one zip per portal. For CrazyGames, the only thing they had to add was saving progress through the SDK Data Module, which took one $1.01 pass.
- Hosting. One Node process on Lizard, at about 19 cents a month by their numbers.
The result
bobaaa says the build passed the CrazyGames SDK check 7 of 7 on the first try. Four days in, the numbers showed 51 visitors, 13 who opened the game, 6 who started a run and 0 who finished one. After a pass that made the first island winnable in under 30 seconds for most people, they say 62 islands were saved over the next four days. The first CrazyGames day brought 141 impressions, a 1.4% click rate, about 3 minutes of play and 0 crashes. That click rate was in the bottom 20%, so their first fix was the cover.
How to build something similar
- Write your game's core rule in one sentence, then a one-page doc, before you prompt anything.
- Give the agent one feature per run, with a finish line you can check by playing and a list of things that must not change.
- Add basic analytics early and fix the first minute of play before adding more content.
- Read your target portal's SDK and QA requirements before you build, and route saving and ads through one adapter.
The original post
Claude Opus 5.5 can take a game from an empty folder to a live portal in 9 days It writes the code, draws the art, records its own trailer and passes the portal's QA In this article, I show you how, step by step https://x.com/i/article/2112472576832258048 From an empty folder to a game strangers play on CrazyGames: one rule, a one-page doc, short Opus passes, a build that saves through the portal's SDK, and the numbers that tell you what to fix next. Most people who try to make a game with AI type "make me a game", get a demo that looks fine for ten seconds, and quit. They don't know which rule to start from. They don't know how to brief the model so it finishes. And nobody tells them what happens after it runs on localhost. I built Skyhold this way. Houses arrive under balloons, you drop each one onto a floating island, and every house tips it. Opus 5.5 wrote every line: 22 passes, about $164. Nine days after an empty folder it passed CrazyGames' SDK check 7 of 7 on the first try and went live in front of their players. This course is the whole route, at a scale you can finish in a few evenings. 01. The rule - one idea a stranger gets in 2 seconds Every game that works on a portal can be explained before the first tap. Mine is: the island has a centre of mass. That one sentence decides everything downstream. Houses have weight. Weight tips the island. Past 15° the edge starts to slide into the clouds. Lose five homes and the island flips. You never have to explain a menu, because the rule is the tutorial. Before you open Claude Code, write your rule in one line. If you need "and" twice, it's two games. 02. The doc - one page before any code Don't ask Opus for a game. Give it a game doc: the rule, the loop, how you win, how you lose, the camera, the controls on desktop and phone, and what "done for today" means. Prompt 1. The day-one brief My first pass took 46 minutes and came back with a playable island. Ugly in places, but playable, and that's the only goal of day one. 03. The passes - one system per Opus run The biggest mistake is one giant prompt for the whole game. Run each feature as its own pass and give each pass one finish line. Every brief has the same five parts: Read these files first (and skip the big library files). Do exactly this one thing. Keep these things working exactly as they are. Done means [something I can check by playing]. Do not open a browser. No runtime errors. The "keep" line is the one people skip. Without it, every pass quietly rewrites something you already accepted. The JSON output gives you the real cost of each run, so you always know what a feature cost you. My most expensive pass was $12.94 (the arcade loop). The cheapest was $1.01. 04. The stack - no engine, no image files three.js for the world. Everything else drawn in code: low-poly houses, balloons, clouds, the UI, even the two mascots. One pass gave the game Moss and Puff for $5.14 in 14 minutes, as SVG in a single module. No image files means no asset pipeline, no licences to check, and a build that ends up tiny. Mine is 1.5 MB in total. 05. The trailer - let the game record itself Add a ?capture mode: a fixed-size canvas, a deterministic window.render(t), and a scripted demo that plays the real game. Then record it frame by frame with a headless browser. Every video I've posted about the game came from the game's own engine. No screen recorder, no editor. When the game changes, you re-record the trailer in minutes, and it always matches what players will see. 06. The funnel - measure the first minute before you add features Four days in I had a game with five story islands, a daily island and a leaderboard. Then I looked at the numbers: 51 visitors, 13 opened the game, 6 started a run, 0 finished one. Nobody needed a fifth island. They needed the first minute to work. Prompt 2. Fix the funnel After that pass the first island became "keep 6 homes standing", which takes most people under 30 seconds to win. 62 islands got
Want to build something like this?
Join the Shipping Skool community free. Paid members get live bootcamp calls every week.
Join Shipping Skool — Free