AGENT SKILL

game-development

Game development orchestrator. Routes to platform-specific skills based on project needs.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
game-development
risk
unknown
source
community
date_added
2026-02-27
description
Game development orchestrator. Routes to platform-specific skills based on project needs.

03 SKILL.md 正文

Game Development

Orchestrator skill that provides core principles and routes to specialized sub-skills.


When to Use This Skill

You are working on a game development project. This skill teaches the PRINCIPLES of game development and directs you to the right sub-skill based on context.


Sub-Skill Routing

Platform Selection

If the game targets... Use Sub-Skill
Web browsers (HTML5, WebGL) game-development/web-games
Mobile (iOS, Android) game-development/mobile-games
PC (Steam, Desktop) game-development/pc-games
VR/AR headsets game-development/vr-ar

Dimension Selection

If the game is... Use Sub-Skill
2D (sprites, tilemaps) game-development/2d-games
3D (meshes, shaders) game-development/3d-games

Specialty Areas

If you need... Use Sub-Skill
GDD, balancing, player psychology game-development/game-design
Multiplayer, networking game-development/multiplayer
Visual style, asset pipeline, animation game-development/game-art
Sound design, music, adaptive audio game-development/game-audio

Core Principles (All Platforms)

1. The Game Loop

Every game, regardless of platform, follows this pattern:

INPUT  → Read player actions
UPDATE → Process game logic (fixed timestep)
RENDER → Draw the frame (interpolated)

Fixed Timestep Rule:

  • Physics/logic: Fixed rate (e.g., 50Hz)
  • Rendering: As fast as possible
  • Interpolate between states for smooth visuals

2. Pattern Selection Matrix

Pattern Use When Example
State Machine 3-5 discrete states Player: Idle→Walk→Jump
Object Pooling Frequent spawn/destroy Bullets, particles
Observer/Events Cross-system communication Health→UI updates
ECS Thousands of similar entities RTS units, particles
Command Undo, replay, networking Input recording
Behavior Tree Complex AI decisions Enemy AI

Decision Rule: Start with State Machine. Add ECS only when performance demands.


3. Input Abstraction

Abstract input into ACTIONS, not raw keys:

"jump"  → Space, Gamepad A, Touch tap
"move"  → WASD, Left stick, Virtual joystick

Why: Enables multi-platform, rebindable controls.


4. Performance Budget (60 FPS = 16.67ms)

System Budget
Input 1ms
Physics 3ms
AI 2ms
Game Logic 4ms
Rendering 5ms
Buffer 1.67ms

Optimization Priority:

  1. Algorithm (O(n²) → O(n log n))
  2. Batching (reduce draw calls)
  3. Pooling (avoid GC spikes)
  4. LOD (detail by distance)
  5. Culling (skip invisible)

5. AI Selection by Complexity

AI Type Complexity Use When
FSM Simple 3-5 states, predictable behavior
Behavior Tree Medium Modular, designer-friendly
GOAP High Emergent, planning-based
Utility AI High Scoring-based decisions

6. Collision Strategy

Type Best For
AABB Rectangles, fast checks
Circle Round objects, cheap
Spatial Hash Many similar-sized objects
Quadtree Large worlds, varying sizes

Anti-Patterns (Universal)

Don't Do
Update everything every frame Use events, dirty flags
Create objects in hot loops Object pooling
Cache nothing Cache references
Optimize without profiling Profile first
Mix input with logic Abstract input layer

Routing Examples

Example 1: "I want to make a browser-based 2D platformer"

→ Start with game-development/web-games for framework selection → Then game-development/2d-games for sprite/tilemap patterns → Reference game-development/game-design for level design

Example 2: "Mobile puzzle game for iOS and Android"

→ Start with game-development/mobile-games for touch input and stores → Use game-development/game-design for puzzle balancing

Example 3: "Multiplayer VR shooter"

→ game-development/vr-ar for comfort and immersion → game-development/3d-games for rendering → game-development/multiplayer for networking


Remember: Great games come from iteration, not perfection. Prototype fast, then polish.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1