Token导航 LogoToken导航

Agent Skill · 研究检索

game-architect(游戏架构师)

game-architect 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

game-architect 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 62,939。

总安装 324周安装 13GitHub Stars 13下载 105核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:game-architect(游戏架构师)
来源仓库:https://github.com/yuki001/game-dev-skills
仓库路径:skills/game-architect
安装命令:
npx skills add https://github.com/yuki001/game-dev-skills --skill game-architect
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yuki001/game-dev-skills --skill game-architect

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,支持快速定位候选结果。适合根据关键词、任务场景或来源线索进行信息收集。安装命令:npx skills add https://github.com/yuki001/game-dev-skills --skill game-architect。

使用前建议确认权限范围和是否会触发联网或文件操作。可参考来源仓库 README 了解具体搜索逻辑和输出格式。

来源仓库内路径:skills/game-architect

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/yuki001/game-dev-skills --skill game-architect;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

game-architect 怎么安装?

在终端执行 npx skills add https://github.com/yuki001/game-dev-skills --skill game-architect。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

game-architect 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

game-architect 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

game-architect 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

game-architect 用的人多吗?

公开数据是累计安装 324 次,近一周安装 13 次,下载 105 次,GitHub 13 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

game-architect 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
game-architect

游戏架构师 · 本页

32413需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Game Architect Skill

Game architecture domain knowledge reference. Provides paradigm selection, system design references for game project architecture.

[!NOTE] This skill contains domain knowledge only, not a workflow. Pair it with a workflow skill (e.g., OpenSpec, SpecKit) or an agent's plan mode for structured design flow.

Usage Modes

With Workflow Skill (Recommended)

When used with a workflow skill (e.g., OpenSpec, SpecKit) or in the plan mode of an agent, this skill serves as a domain knowledge plugin:

  • During requirements/spec phases: Consult the Paradigm Selection Guide and System-Specific References to inform architectural decisions
  • During design/planning phases: Use the Reference Lookup Guide below to read relevant references/ documents

Knowledge Mode (Query)

When user requests to query knowledge for game architecture, this skill provides a reference lookup guide to relevant references/ documents based on the task.


Reference Lookup Guide

When designing game architecture, read the relevant references/ documents based on the task:

Architecture References

WhenRead
Always (high-level structure)references/macro-design.md
Always (core principles)references/principles.md
Requirement analysisreferences/requirements.md
Choosing DDD paradigmreferences/domain-driven-design.md
Choosing Data-Driven paradigmreferences/data-driven-design.md
Choosing Prototype paradigmreferences/prototype-design.md
Evolution & extensibility reviewreferences/evolution.md
Performance optimization neededreferences/performance-optimization.md
Multiplayer support neededreferences/multiplayer-overview.md
  • For physical architecture design, see the Physical Architecture References table below.
  • For system-specific design, see the System-Specific References table below.
  • For multiplayer system design, see the Multiplayer References table below.

Note: Only read the multiplayer references when multiplayer is needed.

Physical Architecture References

WhenRead
Project structure & file organizationreferences/project-structure.md
Data formats, processing, custom formats, bundles, metadatareferences/data-files.md
Asset conventions & pipelinereferences/asset-conventions.md
Distribution, packaging, hot update, CDN, deploymentreferences/distribution.md

System-Specific References

System CategoryReference
Foundation & Core (Logs, Timers, Modules, Events, Resources, Audio, Input)references/system-foundation.md
Time & Logic Flow (Update Loops, Async, FSM, Command Queues, Controllers)references/system-time.md
Combat & Scene (Scene Graphs, Spatial Partitioning, ECS/EC, Loading)references/system-scene.md
UI & Modules (Modules Management, MVC/MVP/MVVM, UI Management, Data Binding, Reactive)references/system-ui.md
Skill System (Attribute, Skill, Buff)references/system-skill.md
Action Combat System (HitBox, Damage, Melee, Projectiles)references/system-action-combat.md
Camera, Character & Controller 3C (PlayerController, Physics, Camera, Actor States)references/system-3c.md
Narrative System (Dialogue, Cutscenes, Story Flow)references/system-narrative.md
Game AI System (Movement, Pathfinding, Decision Making, Tactical)references/system-game-ai.md
Mod & DLC System (Plugin Architecture, Config Database, Scripting, Hooks, Extensibility)references/system-mod.md
Procedural Content Generation (PCG) (World/Level Generation, Roguelike, Noise, Simulation)references/system-pcg.md
Algorithm & Data Structures (Pathfinding, Search, Physics, Generic Solver)references/algorithm.md

Multiplayer References

FocusReferenceUse When
Multiplayer overviewreferences/multiplayer-overview.mdDecide client/server responsibility, authority split, and gameplay sync style
Multiplayer protocol and connectionreferences/multiplayer-protocol.mdDesign messages, serialization, Req/Resp/Notify, heartbeat, reconnect
Multiplayer server architecturereferences/multiplayer-server-architecture.mdDesign ownership boundaries, process roles, deployment, persistence, recovery
Common server components and servicesreferences/multiplayer-implementation-common.mdBuild shared infrastructure such as auth, gateway, connector, db, cache, discovery, queue, observability
Room server build playbookreferences/multiplayer-implementation-room.mdBuild a concrete small-to-medium room-based realtime server with join flow, room ownership, settlement, reconnect
Encounter server build playbookreferences/multiplayer-implementation-encounter.mdBuild a concrete turn-based or combat-workflow server with checkpointing, idempotent actions, settlement
Persistent world server build playbookreferences/multiplayer-implementation-world.mdBuild a concrete AOI world server with region ownership, transfer, location registry, reconnect
Deterministic sync, lockstep, and rollbackreferences/multiplayer-deterministic-sync.mdDesign deterministic input-sync architectures, frame pipelines, rollback, replay, and desync handling

Paradigm Selection Guide

ParadigmKeyPointApplicability ScopeExamplesReference
Domain-Driven Design (DDD)OOP & Entity FirstHigh Rule Complexity. Rich Domain Concepts. Many Distinct Entities.Core Combat Logic, Physics Interactions, Damage/Buff Rules, Complex AI Decision.references/domain-driven-design.md
Data-Driven DesignData Layer FirstHigh Content Complexity. Flow Orchestration. Simple Data Management.Content: Quests, Level Design.Flow: Tutorial Flow, Skill Execution, Narrative.Mgmt: Inventory, Shop, Mail, Leaderboard.references/data-driven-design.md
Use-Case Driven PrototypeUse-Case Implementation FirstRapid ValidationGame Jam, Core Mechanic Testing.references/prototype-design.md

Mixing Paradigms

Most projects mix paradigms:

  1. Macro Consistency: All modules follow the same Module Management Framework.
  2. Domain for Core Entities & Rules: Use DDD for systems with high rule complexity, rich domain concepts, and many distinct entities (e.g., Combat Actors, Damage Formulas, AI Decision).
  3. Data for Content, Flow & State: Use Data-Driven for expandable content (Quests, Level Design), flow orchestration (Tutorial, Skill Execution, Narrative), and simple data management (Inventory, Shop).
  4. Hybrid Paradigms:

- 4.1 Entities as Data: Domain Entities naturally hold both data (fields) and behavior (methods). Design entities to be serialization-friendly (use IDs, keep state as plain fields) so they serve both roles without a separate data layer. - 4.2 Flow + Domain: Use data-driven flow to orchestrate the sequence/pipeline, domain logic to handle rules at each step. E.g., Skill System: flow drives cast→channel→apply, domain handles damage calc and buff interactions. - 4.3 Separate Data/Domain Layers: Only when edit-time and runtime representations truly diverge. Use a Bake/Compile step to bridge them. E.g., visual node-graph editors, compiled assets.

  1. Paradigm Interchangeability: Many systems can be validly implemented with either paradigm. E.g., Actor inheritance hierarchy (Domain) ↔ ECS components + systems (Data-Driven); Buff objects with encapsulated rules (Domain) ↔ Tag + Effect data entries resolved by a generic pipeline (Data-Driven). See Selection Criteria table above for trade-off signals.
  2. Integration: Application Layer bridges different paradigms.

Selection Criteria

When both DDD and Data-Driven fit, use these signals:

SignalFavor DDDFavor Data-Driven
Entity interactionsComplex multi-entity rules (attacker × defender × buffs × environment)Mostly CRUD + display, few cross-entity rules
Behavior sourceVaries by entity type, hard to express as pure dataDriven by config tables, designer-authored content
Change frequencyRules change with game balance iterationsContent/flow changes far more often than logic
Performance profileAcceptable overhead for rich object graphsNeeds batch processing, cache-friendly layouts
NetworkingStateful objects acceptableFlat state snapshots preferred (sync, rollback)
Team workflowProgrammers own the logicDesigners need to iterate without code changes

平台分布

Codex

36.61%
按下载量换算38

Claude

27.61%
按下载量换算29

Cursor

18.48%
按下载量换算19

Gemini CLI

8.52%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills