🍄 Nintendo1996Game FreakVERY HARD

Pokémon Red rebuild deck

VERY HARD

You will get a good prototype. The product is what comes after.

Everything mechanical here is a KINDA-plus: the battle maths is published, the data-driven design is exactly what agents are good at, and you will have a working RPG in a fortnight. What you will not have is 151 creature designs and the twenty years of balance behind them. Make your own creatures; that part is more fun anyway, and it is the only legal path.

Difficulty: VERY HARD · 4 of 5
First playable: A project
The original: 12 team-years
Released: 1996 · Nintendo
Genre: RPG

The one-shot build prompt

Build a monster-collecting turn-based RPG. Top-down tile-based overworld, Canvas 2D, saves to localStorage. Original creatures — do not reproduce Nintendo's.

Requirements:
- Overworld: grid movement with a step animation, tile-based collision, warp tiles between maps, tall grass with a per-step encounter roll, and NPCs with facing, dialogue trees and one-time flags.
- Battle system as a strict turn state machine: both sides choose an action, then resolve in speed order with priority moves first. Damage uses the classic formula shape — level and attack scaled against defence, times a random 0.85-1.00 roll, times type effectiveness, times STAB, with a critical-hit branch. Implement it as a pure function so it is testable.
- A type chart as pure JSON data: 15 types, a full effectiveness matrix. Never hard-code type logic in the battle code.
- Creature data as JSON: base stats, growth curve, learnset by level, evolution conditions, catch rate. Stats derive from base stats plus level plus per-instance variance, so two of the same species differ.
- Catching: a probability from catch rate, current HP fraction, ball modifier and status, with the shake animation reflecting the actual roll.
- Status effects (poison, sleep, paralysis, burn) that persist out of battle, plus stat-stage modifiers within a battle.
- Party of six with a box for overflow, an item bag, a shop, and healing points that restore and set the respawn location.
- Two gyms with a level curve, a puzzle, and a leader with a coherent team.

Definition of done: I catch something at 3HP with a status, level it, it evolves, and it beats a gym leader it previously lost to.

Before you start🧰 The toolkit — models, MCP servers, art and 3D

What you lose

151 creature designs, which is the entire product and is Nintendo's
Type balance and movepools tuned across thousands of interactions
The trading and link-cable design that made it a playground phenomenon
A world map with eight gyms of hand-authored pacing

What to steal

An effectiveness matrix with no dominant type

A type chart is a directed graph, and most hand-written ones quietly contain something that beats everything or something nothing counters. An hour of analysis over the matrix surfaces the dominated entries that would otherwise cost you a hundred playtest hours to notice.

ScopeAn evening— build just this, not the game

Build a type-effectiveness matrix editor with a balance analyser. Single self-contained HTML file, DOM table plus Canvas 2D for the charts, no build step.

- An N x N matrix, N adjustable from 6 to 18. Each cell is one of 0, 0.5, 1 or 2. Rows are attackers, columns defenders. Click a cell to cycle it, rename types inline, import and export the whole thing as JSON.
- The analyser is the point. Per type compute: mean offensive multiplier, mean defensive multiplier, how many types it hits for 2, how many resist it. Then flag the failures — any type strictly dominated by another on both offence and defence, any type nothing counters, any type nothing resists, and any pair with no interaction in either direction.
- Render it as a heatmap plus a ranked table, both updating live as I edit cells.
- Ship one deliberately broken sample matrix in the file.

Definition of done: I load the sample and within a second it names the one type that has no counter.

Make it different

Not a clone — Pokémon Red 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.

Term One Room

Pokémon Red, but one level, done properly, set in a wizarding academy. Rendered in claymation with baked light.

Themea wizarding academy

Angleone level, done properly

Lookclaymation with baked light

Build a browser game called "Term One Room".

The pitch in one line: a rpg in the spirit of Pokémon Red, but one level, done properly, set in a wizarding academy.

WHAT THIS IS
Take the SHAPE of Pokémon Red — 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
One level, done properly. A single space, built to a finish quality you could not sustain across twenty. Every prop and every sightline is deliberate.
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 wizarding academy. Institutional rules the player will break, a timetable, houses or factions, and magic taught badly by people with their own agendas.
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
Claymation with baked light. Soft rounded geometry, a fingerprint-style normal texture, stop-motion timing at 12fps for characters while the camera stays at 60.

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.

Prior art — read before you build

Half the time one of these already does what you wanted, and the other half it saves you a week of solving a problem someone documented in 1997.

Did you build it?

0Share on X

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 12 team-years to the counter on the homepage.

Then try these

Or roll something nobody has built yet →

Questions

How hard is Pokémon Red to rebuild with an AI agent?

Yes — every game is buildable at some scope. The question is how hard, and Pokémon Red is VERY HARD (4 of 5). You will get a good prototype. The product is what comes after. The damage formula is published and the data-driven shape is exactly what agents do well; then you are sat in front of 151 empty creature slots, each needing a design, a learnset and a defensible place in the type chart. Reckon on a project to something you can actually play — not to something that matches the 12 team-years Game Freak spent.

What makes Pokémon Red hard to rebuild?

The damage formula is published and the data-driven shape is exactly what agents do well; then you are sat in front of 151 empty creature slots, each needing a design, a learnset and a defensible place in the type chart. 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 an effectiveness matrix with no dominant type — an evening of work.

How long does it take to build a Pokémon Red clone?

Wrong question, and it is worth saying why. Nobody rebuilds Pokémon Red — the original took Game Freak on the order of 12 team-years, released in 1996 on Nintendo. 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 Pokémon Red?

151 creature designs, which is the entire product and is Nintendo's. Type balance and movepools tuned across thousands of interactions. The trading and link-cable design that made it a playground phenomenon. 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.

Get the next game

One email when new games go on the list. No other reason to email you, ever.