🖥️ PC2019Mega Crit GamesVERY HARDSlay the Spire rebuild deck
VERY HARD
Combat, piles and intents run before lunch; the game is 350 cards balanced against 200 relics over fourteen months of weekly public patching, and no prompt performs that.
You will get a good prototype. The product is what comes after.
The engine is not the hard part; a competent agent will have combat, piles and intents running before lunch. Balance is the hard part and there is no prompt for it: two people ran fourteen months of weekly public patches, from early access in November 2017 to 1.0 in January 2019, to land on numbers that look arbitrary and are anything but. Build the card DSL properly, because you will be editing that JSON for months. Seed the RNG from the very first commit, or you will never reproduce the run somebody is complaining about.
- Difficulty
- VERY HARD · 4 of 5
- First playable
- A project
- The original
- 5 team-years
- Released
- 2019 · PC
- Genre
- Roguelike Deckbuilder
Build a single-player roguelike deckbuilder with turn-based combat against telegraphing enemies. Single self-contained HTML file, Canvas 2D or DOM, no build step.
Requirements:
- Turn order is the thing to get right. At the start of the player's turn, in this exact order: wipe all block, restore energy to 3, draw 5. At the end of each side's turn, that side's own buffs and debuffs tick down by one, so a debuff applied on the turn it lands still bites for a full turn. Each enemy then rolls its next move from a weighted table constrained by rules like "may not use this move more than twice consecutively", and that intent is displayed before the player acts.
- Damage order: (base + strength), then x0.75 if the attacker is weakened, then x1.5 if the target is vulnerable, floored once at the end. Block subtracts after all of that.
- Piles: draw, discard, exhaust. Reshuffle discard into draw the moment it empties, including mid-draw.
- Cards, relics, enemies and encounters in JSON, expressed with a small effect DSL of {type, amount, target} steps rather than a function per card.
- Seeded RNG with separate streams for shuffle, card rewards, map generation and enemy moves, so a seed reproduces a run exactly.
- A branching node map over 15 floors: fights, elites, shop, rest, unknown, boss.
Definition of done: entering the same seed twice gives identical first three fights and identical card rewards, and an enemy telegraphing 12 damage deals exactly 12 until I weaken it, then 9.- Around 350 cards and close to 200 relics balanced against each other through fourteen months of public early access
- Four characters whose decks play like four different genres
- Enemy encounters designed so specific card combinations feel like a discovery rather than a spreadsheet
- The daily climb, the leaderboards, and a community that solved the game years ago and still plays it
Telegraphed intent from a constrained move table
Announcing the next attack before the player acts converts a fight from reaction into planning, and it costs you one weighted table plus an icon. The constraint is what sells it: an enemy forbidden from repeating a move three times reads as having a plan rather than a die.
ScopeAn evening— build just this, not the game
Build a telegraphed-combat toy as a single self-contained HTML file, Canvas 2D or DOM, no build step. One player, one enemy, strictly turn-based. The player has three actions: strike for 6, guard for 8 block, and a debuff that halves the enemy's outgoing damage for one turn. Block is wiped at the start of every player turn, so it can never be banked. The enemy chooses its next action at the end of its own turn, drawn from a weighted table loaded from JSON and filtered by constraints: no move more than twice consecutively, and the heavy attack unavailable two turns running. That choice is displayed before the player acts, showing the exact damage number, recalculated live the moment a debuff lands. Seed the RNG so a run repeats exactly. Definition of done: the enemy shows 12 incoming, I apply the debuff, the displayed number drops to 6 before I have ended my turn, and it then deals exactly 6.
Not a clone — Slay the Spire re-themed and cut down to something you can finish. The angle is the important reel: it is what turns a project into a weekend. 5,880 ways to land.
Metro Deck
Slay the Spire, but a deckbuilder version of its combat, set in a superhero city. Rendered in CRT arcade with scanlines.
Build a browser game called "Metro Deck". The pitch in one line: a roguelike deckbuilder in the spirit of Slay the Spire, but a deckbuilder version of its combat, set in a superhero city. WHAT THIS IS Take the SHAPE of Slay the Spire — its core loop, and whatever makes that loop good — and rebuild it as your own game in a different world at a smaller scope. Use your own names, art and audio, which you want anyway: a reskin of somebody else's game is less interesting than a new one that works the same way. THE ANGLE — this is the important constraint, honour it above everything else A deckbuilder version of its combat. Every action becomes a card with a cost. Cards, relics and enemy intents are pure data, and the whole balance surface becomes a spreadsheet you can tune. This is what makes the project finishable. If a decision would push the scope back towards the original's, take the smaller option every time. THE THEME A superhero city. Powers that are verbs, a city built to be traversed with them, and collateral damage the player has to care about. The theme is not a coat of paint. Let it change what the mechanics mean — a reload, a health pack and a locked door should all be things that make sense in this world and nowhere else. LOOK CRT arcade with scanlines. Post-process pass with scanlines, barrel distortion, phosphor bloom and slight chromatic aberration at the edges. Keep it subtle enough to read text through. REQUIREMENTS - Runs in a browser with no build step. Canvas 2D unless the angle genuinely requires 3D, in which case three.js. - Fixed-timestep update loop with interpolated rendering, so it behaves the same at 60Hz and 144Hz. - Every tuning constant in one CONFIG object at the top, exposed as live sliders in a debug panel. You will find the feel by dragging those, not by prompting. - All content — levels, entities, balance numbers — in JSON or plain data files, never inline in the logic. - Audio generated with the Web Audio API rather than asset files. - Respect prefers-reduced-motion: keep the fades, drop the shake and the parallax. BUILD ORDER 1. The core loop with placeholder rectangles, at the reduced scope the angle demands. No theme, no art, no audio. Make it fun as rectangles first. 2. The angle's consequences. Cutting to bots, or to turn-based, or to one level changes the design rather than just shrinking it — find out how and rewrite step 1. 3. The theme, as content and data. 4. The look, applied last as a rendering layer over a game that already works. Start by writing a one-page plan: the core loop, what the angle removes and what that frees you to do properly, and what you are deliberately leaving out. Wait for me to approve it before writing code.
One count per game. No account — it is tied to a salted hash of your IP, which is not stored in a form anyone can reverse. Every build adds 5 team-years to the counter on the homepage.
Then try these
Questions
How hard is Slay the Spire to rebuild with an AI agent?
Yes — every game is buildable at some scope. The question is how hard, and Slay the Spire is VERY HARD (4 of 5). You will get a good prototype. The product is what comes after. Combat, piles and intents run before lunch; the game is 350 cards balanced against 200 relics over fourteen months of weekly public patching, and no prompt performs that. Reckon on a project to something you can actually play — not to something that matches the 5 team-years Mega Crit Games spent.
What makes Slay the Spire hard to rebuild?
Combat, piles and intents run before lunch; the game is 350 cards balanced against 200 relics over fourteen months of weekly public patching, and no prompt performs that. That is why it sits at VERY HARD rather than a tier either side of it. If you want the idea without the project, the transferable part is telegraphed intent from a constrained move table — an evening of work.
How long does it take to build a Slay the Spire clone?
Wrong question, and it is worth saying why. Nobody rebuilds Slay the Spire — the original took Mega Crit Games on the order of 5 team-years, released in 2019 on PC. What you can do is reach something playable and genuinely yours in about a project, and then keep going for as long as it stays interesting. Any figure that claims otherwise is measuring a prototype and calling it a game.
What do I lose by building my own Slay the Spire?
Around 350 cards and close to 200 relics balanced against each other through fourteen months of public early access. Four characters whose decks play like four different genres. Enemy encounters designed so specific card combinations feel like a discovery rather than a spreadsheet. Those are the parts a prompt will not hand you.
Which AI coding agent should I use to build it?
Any of Claude Code, Codex or Cursor will handle this prompt. Paste it as your first message, let the agent scaffold the project, then iterate on feel — the second, third and tenth prompts are where a game actually gets good. Work in an empty folder or a fresh git branch so you can throw it away cheaply.
One email when new games go on the list. No other reason to email you, ever.