开源项目解析
Claude Code Game Studios
把一个 Claude Code 会话组织成一间工作室:49 个 agent 分导演 / 部门主管 / 专才三层,74 个斜杠命令覆盖从头脑风暴到发版,外加 15 个钩子、14 条规则、62 份文档模板。
读懂层
2 张 · 架构图 / 时序图
DeepWiki · 抓取 2026-08-17 · 核验 2026-08-17
DeepWiki · 抓取 2026-08-17 · 核验 2026-08-17
全部是 `.claude/` 下的 Markdown 与 shell:agents / skills / hooks / rules / docs。没有服务、没有依赖,clone 下来就是一套配置。
它管哪几个决定
自持能力
动手层
装它要过哪几关
- 1克隆仓库到你的游戏工程根目录它整套东西都在 `.claude/` 下 —— 放错层级 Claude Code 就看不见
- 2在 Claude Code 里跑 `/start`先跑这一条,它会探测工程处于哪个阶段再给你路线,跳过这一步等于放弃了它的编排
- 3`/setup-engine` 选引擎Godot / Unity / 虚幻三套专家角色互斥,选错了后面所有建议都对不上
- 4安装 Python 3,建议同时安装 jq当前 README 明确:无 Python 时配置回退默认值,涉及数据 JSON 的提交会阻止,不能笼统当作可选依赖。
改哪个文件能改什么
.claude/agents/49 个角色的定义。想改某个角色的判断标准,改这里.claude/skills/74 个斜杠命令。每个是一份 SKILL.md.claude/hooks/提交与推送时跑的校验脚本.claude/docs/templates/62 份文档模板,设计文档的骨架从这里来坑在哪一处
带 issue 编号的来自:github issues 按回复数排序 · 核验 2026-08-17
教程
没找到官方口径的教程 —— 官方只给了 README。
项目自述
以下是仓库 README 的开头部分(原文引用,抓取 2026-08-17)。读全文 ↗
Claude Code Game Studios
Turn a single Claude Code session into a full game development studio.
49 agents. 74 skills. One coordinated AI team.
Why This Exists
Building a game solo with AI is powerful — but a single chat session has no structure. No one stops you from hardcoding magic numbers, skipping design docs, or writing spaghetti code. There's no QA pass, no design review, no one asking "does this actually fit the game's vision?"
Claude Code Game Studios solves this by giving your AI session the structure of a real studio. Instead of one general-purpose assistant, you get 49 specialized agents organized into a studio hierarchy — directors who guard the vision, department leads who own their domains, and specialists who do the hands-on work. Each agent has defined responsibilities, escalation paths, and quality gates.
The result: you still make every decision, but now you have a team that asks the right questions, catches mistakes early, and keeps your project organized from first brainstorm to launch.
Table of Contents
- What's Included
- Studio Hierarchy
- Slash Commands
- Does it produce games, or documents?
- Getting Started
- Configuration
- Upgrading
- Project Structure
- How It Works
- Design Philosophy
- Customization
- Platform Support
- Community
- Supporting This Project
- License
What's Included
| Category | Count | Description |
| Agents | 49 | Specialized subagents across design, programming, art, audio, narrative, QA, and production |
| Skills | 74 | Slash commands for every workflow phase (/start, /design-system, /create-epics, /create-stories, /dev-story, /story-done, etc.) |
| Hooks | 15 | Automated validation on commits, pushes, asset changes, design-doc reads, writes and registries, session lifecycle, agent audit trail, and gap detection |
| Rules | 14 | Path-scoped coding standards enforced when editing gameplay, engine, AI, UI, network code, scene and asset files, and more |
| Templates | 62 | Document templates for GDDs, UX specs, ADRs, sprint plans, HUD design, accessibility, and more |
Studio Hierarchy
Agents are organized into three tiers, matching how real studios operate:
Tier 1 — Directors
creative-director technical-director producer
Tier 2 — Department Leads
game-designer lead-programmer art-director
audio-director narrative-director qa-lead
release-manager localization-lead
Tier 3 — Specialists
gameplay-programmer engine-programmer ai-programmer
network-programmer tools-programmer ui-programmer
systems-designer level-designer economy-designer
technical-artist sound-designer writer
world-builder ux-designer prototyper
performance-analyst devops-engineer analytics-engineer
security-engineer qa-tester accessibility-specialist
live-ops-designer community-manager
Each agent declares a model in its frontmatter: the three directors ask for
Opus, lead-programmer and fifteen specialists name Sonnet, and the remaining thirty
inherit your session's model. Treat the tiers as seniority of role, not as
a billing plan — most of the studio runs on whatever model you are
……(后略,见原文)自述与实测
星速全场最高,但社区自己在追问「有人真做出来过吗」,至今没人拿得出成品
它自己说
把一个会话组织成一间工作室:49 个 agent、73 个流程命令、三大引擎各配专家
实际撞到的
issue #34(12 条回复)问「有人做出过完整能玩的游戏吗」——两位重度用户分别在第 5 个与第 62 个冲刺,都还没发布;另有人直接说「我到现在没看到它真产出过游戏」。中文 issue #53 里多位用户:「一直在产生文档」「跑了十来天,一行代码不带写,硬逼着写 demo 出来非常粗糙」
判断
优势
- 把「一个人配一个 AI」补成了「有人评审、有人验收」
- Godot / Unity / 虚幻三套专家角色都给了,不用自己写
- 钩子在提交时拦,规矩不靠自觉
局限
- README 自己写明「你仍然做每一个决定」 —— 它不替你定玩法
- 只对 Claude Code 有效,换个客户端整套失效
- 角色和命令加起来一百多个,第一次用光是读清单就是负担
不适用
想让它自己把游戏做出来 —— 它管的是分工与流程,一行引擎代码都不替你跑。
同管这些决定的其它项目
github README + DeepWiki · 核验 2026-10-19 | 判断栏可报错。