Skip to main content
prompt GP ChatGPT

Unity Game Project taste — ChatGPT prompt for Unity projects

Unity Game Project taste — a prompt for ChatGPT that sets engineering guidelines for Unity game projects. It covers code structure, assets, testing, and builds.

CC0-1.0 ★ 178,201 updated 2026-10-24

Open on GitHub

What Unity Game Project taste does

This prompt lays out engineering guidelines for a Unity project: pin the editor version, track binary assets with Git LFS, and split code into feature-level assembly definitions. It recommends keeping gameplay logic in plain C# classes and using MonoBehaviours as thin adapters. Designer-adjustable data belongs in ScriptableObjects.

The guidance also covers profiling, Addressables, input handling, and prefab structure. It calls for profiling on the slowest target device, not just in the editor. For CI, it recommends running Edit Mode and Play Mode tests on each pull request and building target platforms automatically.

Save data should carry a version, with older saves migrated during loading. The Claude Code file path is .claude/commands/prompts.csv.md.

What it helps with

  • set Unity editor version and Git LFS conventions
  • separate gameplay logic from MonoBehaviour components
  • choose approaches for Addressables, input, and object pooling
  • define Unity CI tests and platform builds
  • plan migration for older save data

Example prompts for the agent

  • Apply these guidelines to the architecture of my Unity project.
  • Review how this Unity project handles tests and builds.
  • Suggest a structure for the game's code, prefabs, and data using these guidelines.

How to install Unity Game Project taste

How to use

Paste the text at the start of a chat or into project instructions

Questions about Unity Game Project taste

How do I install Unity Game Project taste in Claude Code?

Add the prompt file at .claude/commands/prompts.csv.md.

What does Unity Game Project taste do?

It gives engineering guidelines for Unity game architecture, asset handling, profiling, tests, and CI builds.

What CI checks does it recommend?

It recommends Edit Mode and Play Mode tests on each pull request, plus automated builds for target platforms.

Source text

prompts.csv · CC0-1.0
# Unity Game Project taste of a shipping-focused game developer
- Pin the Unity editor to one LTS version per project and upgrade it deliberately in its own branch. Confidence: 0.90
- Use Git with Git LFS for binary assets, plus a .gitattributes file and Unity's smart merge tool for scenes and prefabs. Confidence: 0.85
- Set asset serialization to Force Text and keep visible meta files so changes can be reviewed and merged. Confidence: 0.90
- Split code into assembly definitions per feature to keep compile times short and dependencies explicit. Confidence: 0.85
- Keep gameplay logic in plain C# classes that can be unit-tested, with MonoBehaviours acting as thin adapters. Confidence: 0.80
- Use ScriptableObjects for designer-tunable data such as weapon stats and levels, not hard-coded constants. Confidence: 0.85
- Avoid GameObject.Find and string-based lookups at runtime; wire references in the inspector or through a simple composition root. Confidence: 0.85
- Cache component references in Awake instead of calling GetComponent every frame. Confidence: 0.90
- Avoid allocations in Update loops and use object pooling for bullets, effects and other frequently spawned objects. Confidence: 0.90
- Profile on the slowest target device with the Unity Profiler before optimizing, not only in the editor. Confidence: 0.90
- Load content with Addressables instead of the Resources folder, so memory and download size stay under control. Confidence: 0.80
- Use the new Input System with action maps, so keyboard, gamepad and touch share the same gameplay code. Confidence: 0.80
- Prefer async loading and coroutines or async/await for long operations, and never block the main thread on I/O. Confidence: 0.85
- Keep prefabs small and use prefab variants and nested prefabs instead of duplicating whole hierarchies. Confidence: 0.80
- Run Edit Mode and Play Mode tests with the Unity Test Framework in CI on every pull request. Confidence: 0.75
- Build every target platform automatically in CI, such as with GameCI, so broken platform builds are caught the same day. Confidence: 0.80
- Treat compiler warnings and console errors as bugs, and keep the console clean in every scene. Confidence: 0.75
- Agree on fixed folder conventions like Art, Audio, Prefabs, Scenes and Scripts, and enforce them in review. Confidence: 0.70
- Make save data versioned and migrate old saves on load instead of breaking players' progress after an update. Confidence: 0.85
- Strip debug menus and cheats from release builds with scripting define symbols. Confidence: 0.80

© f · CC0-1.0 · f/prompts.chat

Similar prompts

All prompts for Game dev and 3D: Unity, Unreal, Godot, Blender →

From the same set218

The whole set →
Neovim Config taste The Neovim Config taste ChatGPT prompt sets out a terminal-first style for building a Neovim configuration in Lua. It covers plugin loading, language tools, formatting, and key bindings. GP ChatGPT ★ 178,201repo stars API Client SDK taste API Client SDK taste — a prompt for ChatGPT that defines developer-experience standards for building API client SDKs. It runs during API architecture design, OpenAPI code generation, and error-handling setup. GP ChatGPT ★ 178,201repo stars dbt Analytics Project taste dbt Analytics Project taste — a prompt for ChatGPT sets conventions for dbt models, tests, documentation, and CI. Use it while shaping an analytics project or revising its model structure. GP ChatGPT ★ 178,201repo stars Design System taste Design System taste — a prompt for ChatGPT that enforces pragmatic design system standards, tokens, accessibility, and component architecture. GP ChatGPT ★ 178,201repo stars Ansible Playbook taste Ansible Playbook taste — a prompt for ChatGPT, Claude.ai, and Claude Code setting standards for infrastructure code. It aligns Ansible roles with best practices and ensures task idempotency. GP ChatGPT ★ 178,201repo stars Embedded Firmware taste Embedded Firmware taste — a prompt for ChatGPT that enforces reliability-minded engineering standards for embedded firmware development. GP ChatGPT ★ 178,201repo stars WebAssembly Module taste WebAssembly Module taste — a system prompt for ChatGPT, Claude.ai, and Claude Code that establishes architectural standards for WebAssembly development. It guides developers on performance and safety best practices. GP ChatGPT ★ 178,201repo stars Incident Response taste The Incident Response taste prompt for ChatGPT sets out how a calm on-call engineer can handle incidents. It calls for early declaration and coordinated response before the root cause is known. GP ChatGPT ★ 178,201repo stars

Project sponsors

Companies that keep this analytics open