配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。

MITAuto-check passedAgent Workflows

Install Setup Engine

skills CLI
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill setup-engine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pixel-cellar/Claude-Code-Game-Studios setup-engine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/setup-engine .claude/skills/setup-engine && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
setup-engine
GitHub stars
342
Token cost
~1.5k tokens
SKILL.md length
367 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。

  • Works in 11 steps: 解析参数 → 引导模式(无参数) → 查找当前版本 → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers 1. 解析参数, 2. 引导模式(无参数), 3. 查找当前版本 and 4. 更新 CLAUDE.md 技术栈, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Setup Engine is an agent skill from pixel-cellar/Claude-Code-Game-Studios. 配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files and Game development. It works with Godot, C# and C++. The repository describes itself as: 48 协同代理管理独立游戏开发的 Claude Code 架构 (中文本地化版本). The licence is MIT.

When your agent uses it

  • Tasks that involve Agent instruction files
  • Tasks that involve Game development

Example prompts

  • “/setup-engine”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Write, Edit, WebSearch, WebFetch, Task

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. 解析参数
  2. 引导模式(无参数)
  3. 查找当前版本
  4. 更新 CLAUDE.md 技术栈
  5. 填充技术偏好
  6. 确定知识缺口
  7. 填充引擎参考文档
  8. 更新 CLAUDE.md 导入
  9. 更新 Agent 指令
  10. Refresh 子命令
  11. 输出摘要

What it can do on your machine

Read from SKILL.md and the folder at commit 2c016ef. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Write
    • Edit
    • WebSearch
    • WebFetch
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setup Engine loads about 1.5k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pixel-cellar/Claude-Code-Game-Studios at commit 2c016ef, republished under its MIT licence (© pixel-cellar). 367 words, ~1,511 tokens.

Download SKILL.mdSave it as .claude/skills/setup-engine/SKILL.md (or your agent's skills folder).
name
setup-engine
description
配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。
allowed-tools
Read, Glob, Grep, Write, Edit, WebSearch, WebFetch, Task
argument-hint
[engine version] or no args for guided selection
user-invocable
true

当此技能被调用时:

1. 解析参数

三种模式:

  • 完整规格:/setup-engine godot 4.6 — 已提供引擎和版本
  • 仅引擎:/setup-engine unity — 已提供引擎,版本将自动查找
  • 无参数:/setup-engine — 完全引导模式(引擎推荐 + 版本选择)

2. 引导模式(无参数)

如果未指定引擎,运行交互式引擎选择流程:

检查现有游戏概念
  • 如果存在,读取 design/gdd/game-concept.md — 提取游戏类型、范围、目标平台、美术风格、团队规模,以及 /brainstorm 给出的引擎推荐
  • 如果概念不存在,告知用户:

    "未找到游戏概念。建议先运行 /brainstorm 发现你想构建什么 — 它还会推荐引擎。或者告诉我你的游戏想法,我可以帮你选择。"

如果用户想在无概念的情况下选择,询问:
  1. 什么类型的游戏?(2D、3D,或两者兼具?)
  2. 什么平台?(PC、移动端、主机、网页?)
  3. 团队规模和经验?(单人新手、单人经验丰富、小团队?)
  4. 有强烈的语言偏好吗?(GDScript、C#、C++、可视化脚本?)
  5. 引擎授权预算?(仅免费,还是可接受商业授权?)
给出推荐

使用以下决策矩阵:

因素Godot 4UnityUnreal Engine 5
最适用于2D 游戏、小型 3D、单人/小团队移动端、中等规模 3D、跨平台3A 级 3D、照片级写实、大型团队
语言GDScript(+ C#,通过扩展支持 C++)C#C++ / Blueprint
费用免费,MIT 许可证收入门槛以下免费收入门槛以下免费,5% 版税
学习曲线平缓中等陡峭
2D 支持优秀(原生)良好(但以 3D 为优先)可行但非理想选择
3D 质量上限良好(快速提升中)非常好业界领先
Web 导出支持(原生)支持(有限制)不支持
主机导出通过第三方支持(需要授权)支持
开源是否源码可用

给出排名前 1-2 的推荐及其与用户回答相关联的理由。 让用户自行选择 — 永远不要强制推荐。


3. 查找当前版本

引擎确定后:

  • 如果提供了版本,直接使用
  • 如果未提供版本,使用 WebSearch 查找最新稳定版:
    • 搜索:"[engine] latest stable version [当前年份]"
    • 与用户确认:"最新稳定版 [引擎] 是 [版本]。使用这个吗?"

4. 更新 CLAUDE.md 技术栈

读取 CLAUDE.md 并更新技术栈部分。将 [CHOOSE] 占位符替换为实际值:

Godot:

markdown
- **引擎**:Godot [版本]
- **语言**:GDScript(主要),通过 GDExtension 支持 C++(性能关键场景)
- **构建系统**:SCons(引擎),Godot 导出模板
- **资产管线**:Godot 导入系统 + 自定义资源管线

Unity:

markdown
- **引擎**:Unity [版本]
- **语言**:C#
- **构建系统**:Unity Build Pipeline
- **资产管线**:Unity Asset Import Pipeline + Addressables

Unreal:

markdown
- **引擎**:Unreal Engine [版本]
- **语言**:C++(主要),Blueprint(游戏玩法原型开发)
- **构建系统**:Unreal Build Tool (UBT)
- **资产管线**:Unreal Content Pipeline

5. 填充技术偏好

更新 CLAUDE.md 后,创建或更新 .claude/docs/technical-preferences.md,填入引擎对应的默认值。先阅读现有模板,然后填入:

引擎和语言部分
  • 根据第 4 步的引擎选择填入
命名约定(引擎默认值)

Godot (GDScript):

  • 类名:PascalCase(如 PlayerController)
  • 变量/函数:snake_case(如 move_speed)
  • 信号:snake_case 过去时(如 health_changed)
  • 文件名:snake_case 与类名匹配(如 player_controller.gd)
  • 场景:PascalCase 与根节点匹配(如 PlayerController.tscn)
  • 常量:UPPER_SNAKE_CASE(如 MAX_HEALTH)

Unity (C#):

  • 类名:PascalCase(如 PlayerController)
  • 公共字段/属性:PascalCase(如 MoveSpeed)
  • 私有字段:_camelCase(如 _moveSpeed)
  • 方法:PascalCase(如 TakeDamage())
  • 文件名:PascalCase 与类名匹配(如 PlayerController.cs)
  • 常量:PascalCase 或 UPPER_SNAKE_CASE

Unreal (C++):

  • 类名:带前缀的 PascalCase(A 表示 Actor,U 表示 UObject,F 表示结构体)
  • 变量:PascalCase(如 MoveSpeed)
  • 函数:PascalCase(如 TakeDamage())
  • 布尔值:b 前缀(如 bIsAlive)
  • 文件名:与类名匹配但不带前缀(如 PlayerController.h)
其余部分
  • 性能预算:保留为 [TO BE CONFIGURED] 并附带建议:

    "典型目标:60fps / 16.6ms 帧预算。现在设置这些吗?"

  • 测试:建议引擎对应的框架(Godot 用 GUT,Unity 用 NUnit 等)
  • 禁止模式/允许的库:保留为占位符
协作步骤

向用户展示填好的偏好设置:

"这是 [引擎] 的默认技术偏好。要自定义其中任何一项,还是直接保存默认值?"

等待用户批准后再写入文件。


Show full SKILL.md (169 more words)Show less

6. 确定知识缺口

检查引擎版本是否可能超出 LLM 的训练数据。

已知的大致覆盖范围(随着模型更新调整):

  • LLM 知识截止日期:2025 年 5 月
  • Godot:训练数据可能覆盖到 ~4.3
  • Unity:训练数据可能覆盖到 ~2023.x / 6000.x 早期版本
  • Unreal:训练数据可能覆盖到 ~5.3 / 5.4 早期版本

将用户选择的版本与这些基线进行比较:

  • 在训练数据范围内 → 低风险 — 参考文档可选但推荐
  • 接近边界 → 中风险 — 推荐参考文档
  • 超出训练数据 → 高风险 — 必须有参考文档

告知用户所属的类别及原因。


7. 填充引擎参考文档

如果在训练数据范围内(低风险):

创建一个精简的 docs/engine-reference/<engine>/VERSION.md:

markdown
# [Engine] — 版本参考

| 字段 | 值 |
|------|-----|
| **引擎版本** | [版本] |
| **项目锁定日期** | [今天的日期] |
| **LLM 知识截止** | 2025 年 5 月 |
| **风险等级** | 低 — 版本在 LLM 训练数据范围内 |

## 说明

此引擎版本在 LLM 的训练数据范围内。引擎参考文档为可选项,
但如果代理建议了错误的 API,可稍后添加。

随时运行 `/setup-engine refresh` 来填充完整参考文档。

不要创建 breaking-changes.md、deprecated-apis.md 等文件 — 它们会增加上下文成本但价值有限。

如果超出训练数据(中风险或高风险):

通过搜索网络创建完整的参考文档集:

  1. 搜索官方迁移/升级指南:

    • "[engine] [旧版本] 到 [新版本] 迁移指南"
    • "[engine] [版本] breaking changes"
    • "[engine] [版本] changelog"
    • "[engine] [版本] deprecated API"
  2. 从官方文档获取并提取:

    • 从知识截止到当前版本之间的每个版本的 breaking changes
    • 已废弃的 API 及其替代方案
    • 新功能和最佳实践
  3. 创建完整的参考目录:

    docs/engine-reference/<engine>/
    ├── VERSION.md              # 版本锁定 + 知识缺口分析
    ├── breaking-changes.md     # 逐版本的 breaking changes
    ├── deprecated-apis.md      # "不要用 X → 用 Y" 对照表
    ├── current-best-practices.md  # 知识截止后的新实践
    └── modules/                # 各子系统参考(按需创建)
  4. 使用网络搜索的真实数据填充每个文件,遵循现有参考文档的格式。每个文件必须有"最后验证:[日期]"标题。

  5. 对于模块文件:仅对发生了重大变化的子系统创建模块。不要创建空白或内容稀少的模块文件。


8. 更新 CLAUDE.md 导入

更新"引擎版本参考"下的 @ 导入,指向正确的引擎:

markdown
## 引擎版本参考

@docs/engine-reference/<engine>/VERSION.md

如果之前的导入指向不同引擎(例如从 Godot 切换到 Unity),请更新。


9. 更新 Agent 指令

对于所选引擎的专家代理,验证它们是否有"版本感知"部分。如果没有,按照现有 Godot 专家代理的模式添加。

该部分应指示代理:

  1. 读取 docs/engine-reference/<engine>/VERSION.md
  2. 建议代码前检查已废弃的 API
  3. 检查相关版本过渡的 breaking changes
  4. 使用 WebSearch 验证不确定的 API

10. Refresh 子命令

如果以 /setup-engine refresh 调用:

  1. 读取现有的 docs/engine-reference/<engine>/VERSION.md 获取当前引擎和版本
  2. 使用 WebSearch 检查:
    • 自上次验证以来的新引擎发布
    • 更新的迁移指南
    • 新废弃的 API
  3. 用新发现更新所有参考文档
  4. 更新所有修改文件的"最后验证"日期
  5. 报告变更内容

11. 输出摘要

设置完成后,输出:

引擎设置完成
=====================
引擎:            [名称] [版本]
知识风险:        [低/中/高]
参考文档:        [已创建/已跳过]
CLAUDE.md:       [已更新]
技术偏好:        [已创建/已更新]
代理配置:        [已验证]

后续步骤:
1. 查看 docs/engine-reference/<engine>/VERSION.md
2. [如果来自 /brainstorm] 运行 /map-systems 将概念分解为独立系统
3. [如果来自 /brainstorm] 运行 /design-system 逐系统编写 GDD(引导式,按章节)
4. [如果来自 /brainstorm] 运行 /prototype [核心机制] 测试核心循环
5. [如果是全新开始] 运行 /brainstorm 发现游戏概念
6. 创建第一个里程碑:/sprint-plan new

护栏

  • 绝对不要猜测引擎版本 — 始终通过 WebSearch 或用户确认来验证
  • 没有询问前绝不要覆盖现有参考文档 — 应追加或更新
  • 如果已有不同引擎的参考文档,替换前先询问
  • 始终在编辑 CLAUDE.md 之前向用户展示将要修改的内容
  • 如果 WebSearch 返回模糊结果,展示给用户并让其决定

© pixel-cellar, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/setup-engine of pixel-cellar/Claude-Code-Game-Studios.

Open the folder on GitHubat commit 2c016ef

Compare with similar skills

Setup Engine next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Setup Engine compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setup Engine this skillpixel-cellar/Claude-Code-Game-Studios342—~1.5kAutomated safety check: PassMIT
Beehavejame581/GodotPrompter792—~2.8kAutomated safety check: PassMIT
Headless BuildRandallLiuXin/GodotMaker5491 repos~454Automated safety check: PassCustom licence
Gdextensionjame581/GodotPrompter792—~2.7kAutomated safety check: PassMIT
Limboaijame581/GodotPrompter792—~3.2kAutomated safety check: PassMIT
Godotericrisco/rsc-harness156—~3.6kAutomated safety check: PassMIT

Similar skills

  • Beehave

    jame581/GodotPrompter

    A skill your agent uses when using the Beehave addon — pure-GDScript behavior trees with composites, decorators, leaves, a blackboard, and a visual runtime debugger

    792 GitHub stars~2.8k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Headless Build

    RandallLiuXin/GodotMaker

    Compile-check a Godot project using headless mode. An agent skill from RandallLiuXin/GodotMaker.

    549 GitHub starsUsed in 1 repo~454 tokens
    Game DevelopmentAuto-check passed
  • Gdextension

    jame581/GodotPrompter

    A skill your agent uses when building native extensions for Godot — godot-cpp (C++) or gdext (Rust), binding classes, building, and GDScript/C interop

    792 GitHub stars~2.7k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Limboai

    jame581/GodotPrompter

    A skill your agent uses when using the LimboAI addon — behavior trees and hierarchical state machines (C++ GDExtension) with a visual editor, BTTask subclassing, and a blackboard

    792 GitHub stars~3.2k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Godot

    ericrisco/rsc-harness

    A skill your agent uses when writing, reviewing, or debugging Godot 4.x games in GDScript or C — scenes, nodes, custom Resources, autoload/EventBus signals, typed GDScript, CharacterBody2D/3D…

    156 GitHub stars~3.6k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Unity

    ericrisco/rsc-harness

    A skill your agent uses when writing, reviewing or structuring Unity game code in C for Unity 6 LTS — GameObjects and the Transform hierarchy, the MonoBehaviour lifecycle, prefabs and variants…

    156 GitHub stars~4k tokensUpdated yesterday
    Game DevelopmentAuto-check passed

More from pixel-cellar/Claude-Code-Game-Studios

All 23 skills in this repo
  • Patch Notes

    pixel-cellar/Claude-Code-Game-Studios

    从 git 历史记录、Sprint 数据和内部更新日志生成面向玩家的补丁说明。将开发者语言转化为清晰、有吸引力的玩家沟通内容。

    342 GitHub stars~498 tokensUpdated 6 mo ago
    Auto-check: notes
  • Estimate

    pixel-cellar/Claude-Code-Game-Studios

    通过分析复杂度、依赖关系、历史速度和风险因素来估算任务工作量。生成包含置信水平的结构化估算. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    342 GitHub stars~751 tokensUpdated 6 mo ago
    Auto-check passed
  • Perf Profile

    pixel-cellar/Claude-Code-Game-Studios

    结构化的性能分析工作流。识别瓶颈、与性能预算对比测量,并生成带有优先级排序的优化建议. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    342 GitHub stars~466 tokensUpdated 6 mo ago
    Auto-check: notes
  • Release Checklist

    pixel-cellar/Claude-Code-Game-Studios

    生成全面的发布前验证清单,涵盖构建验证、合规要求、商店元数据和发布准备就绪情况. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    342 GitHub stars~696 tokensUpdated 6 mo ago
    Auto-check passed
  • Retrospective

    pixel-cellar/Claude-Code-Game-Studios

    通过分析已完成的工作、速率、阻碍因素和模式来生成 Sprint 或里程碑回顾。产出可执行的洞见以指导下一次迭代. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    342 GitHub stars~767 tokensUpdated 6 mo ago
    Auto-check passed
  • Sprint Plan

    pixel-cellar/Claude-Code-Game-Studios

    根据当前里程碑、已完成工作和可用产能生成新的冲刺计划或更新现有计划。从生产文档和设计待办事项中拉取上下文. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    342 GitHub stars~481 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Setup Engine

What does Setup Engine do?

配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。. Setup Engine is an agent skill from pixel-cellar/Claude-Code-Game-Studios.

When should I use Setup Engine?

Setup Engine fits situations like: tasks that involve Agent instruction files; tasks that involve Game development.

How do I install Setup Engine in Claude Code?

Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill setup-engine -a claude-code`. Or copy the skill folder (.claude/skills/setup-engine in pixel-cellar/Claude-Code-Game-Studios) into .claude/skills/setup-engine in your project. Claude Code loads it when a task matches its description.

How do I install Setup Engine in Codex?

Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill setup-engine -a codex`. Or copy the skill folder (.claude/skills/setup-engine in pixel-cellar/Claude-Code-Game-Studios) into .agents/skills/setup-engine in your project. Codex loads it when a task matches its description.

Can I use Setup Engine in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill setup-engine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup-engine, .gemini/skills/setup-engine, .github/skills/setup-engine and .opencode/skills/setup-engine in your project.

What does Setup Engine need to run?

SKILL.md names no scripts, command-line tools or credentials: Setup Engine is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, Write, Edit, WebSearch, WebFetch, Task.

Does Setup Engine access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Setup Engine safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Setup Engine use?

Setup Engine is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Setup Engine use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Setup Engine?

Skills that share tags, products or a category with Setup Engine: Beehave (jame581/GodotPrompter, 792 stars), Headless Build (RandallLiuXin/GodotMaker, 549 stars), Gdextension (jame581/GodotPrompter, 792 stars) and Limboai (jame581/GodotPrompter, 792 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setup Engine?

pixel-cellar (a GitHub organization) maintains it in pixel-cellar/Claude-Code-Game-Studios, which has 342 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on March 30, 2026.

Source: pixel-cellar/Claude-Code-Game-Studios on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.