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。
首次入门引导 — 询问你当前处于哪个阶段，然后引导你进入正确的工作流。不做任何假设. An agent skill from pixel-cellar/Claude-Code-Game-Studios.
MITAuto-check passed
Install Start
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios start --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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/start .claude/skills/start && rm -rf skills-srcUse ~/.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/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .claude/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/startType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios start --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/start .agents/skills/start && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .agents/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios start --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/start .cursor/skills/start && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .cursor/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pixel-cellar/Claude-Code-Game-Studios.git --path .claude/skills/start--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios start --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/start .gemini/skills/start && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .gemini/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios startInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/start .github/skills/start && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .github/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pixel-cellar/Claude-Code-Game-Studios start --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/start .opencode/skills/start && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "start" agent skill from https://github.com/pixel-cellar/Claude-Code-Game-Studios/tree/cn-localization/.claude/skills/start into .opencode/skills/start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
start- GitHub stars
- 342
- Token cost
- ~886 tokens
- SKILL.md length
- 250 words
- Files
- 1
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- MIT
At a glance
首次入门引导 — 询问你当前处于哪个阶段，然后引导你进入正确的工作流。不做任何假设. An agent skill from pixel-cellar/Claude-Code-Game-Studios.
- Works in 5 steps: 检测项目状态（静默） → 询问用户当前阶段 → 根据回答进行路由 → …
- SKILL.md covers 工作流, 边界情况 and 协作协议
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Start is an agent skill from pixel-cellar/Claude-Code-Game-Studios. 首次入门引导 — 询问你当前处于哪个阶段，然后引导你进入正确的工作流。不做任何假设。
Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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.
Example prompts
- “/start”
Requirements
- Pre-approved tools (allowed-tools): Read, Glob, Grep, AskUserQuestion
Workflow steps
5 steps, taken from the step headings in SKILL.md.
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:
ReadGlobGrepAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
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
Start loads about 886 tokens when it runs. Until then it costs about 12 tokens; SKILL.md has 250 words of instructions outside code blocks.
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). 250 words, ~886 tokens.
Download SKILL.mdSave it as
.claude/skills/start/SKILL.md (or your agent's skills folder).- name
- start
- description
- 首次入门引导 — 询问你当前处于哪个阶段，然后引导你进入正确的工作流。不做任何假设。
- allowed-tools
- Read, Glob, Grep, AskUserQuestion
- argument-hint
- [无参数]
- user-invocable
- true
引导式入门
此技能是新用户的入口。它不会假设你已经有了游戏创意、引擎偏好或任何经验。它先询问，然后将你路由到正确的工作流。
工作流
1. 检测项目状态（静默）
在询问任何问题之前，静默收集上下文信息，以便量身定制你的引导建议。不要主动展示这些结果 — 它们用于指导推荐，而非作为对话开场白。
检查：
- 引擎已配置？ 读取
.claude/docs/technical-preferences.md。如果 Engine 字段包含[TO BE CONFIGURED]，说明引擎未设置。 - 游戏概念是否存在？ 检查
design/gdd/game-concept.md。 - 源代码是否存在？ 使用 Glob 搜索
src/中的源文件（*.gd、*.cs、*.cpp、*.h、*.rs、*.py、*.js、*.ts）。 - 原型是否存在？ 检查
prototypes/中的子目录。 - 设计文档是否存在？ 统计
design/gdd/中的 Markdown 文件数量。 - 生产工件（Production Artifacts）？ 检查
production/sprints/或production/milestones/中是否有文件。
在内部保存这些发现。你将用它们来验证用户的自评结果并定制后续推荐。
2. 询问用户当前阶段
这是用户首先看到的内容。清晰地展示以下 4 个选项：
欢迎使用 Claude Code Game Studios！
在提出建议之前，我想了解你目前的起点。你的游戏创意现在处于哪个阶段？
A）还没有想法 — 我完全没有任何游戏概念。我想探索并弄清楚要做什么。
B）模糊的想法 — 我有一个粗略的主题、感觉或类型方向（例如"跟太空有关的东西"或"一款温馨的农场游戏"），但还没有具体内容。
C）清晰的概念 — 我知道核心想法 — 类型、基本机制，可能还有一句话的推介 — 但还没有正式形成文档。
D）已有成果 — 我已经有了设计文档、原型、代码或重要的规划工作。我想整理或继续这些工作。
等待用户回答。在用户回复之前不要继续。
3. 根据回答进行路由
如果选 A：还没有想法
用户在进入其他任何环节之前需要创意探索。引擎选择、技术配置 — 这些都以后再说。
- 确认从零开始完全没问题
- 简要说明
/brainstorm的作用（使用专业框架的引导式创意发想 — MDA 框架、玩家心理学、动词优先设计） - 建议下一步运行
/brainstorm open - 展示推荐路径：
/brainstorm— 发现你的游戏概念/setup-engine— 配置引擎（brainstorm 会推荐一个）/map-systems— 将概念拆解为系统并规划 GDD（游戏设计文档）编写顺序/prototype— 测试核心机制/sprint-plan— 规划第一个冲刺（Sprint）
如果选 B：模糊的想法
用户有一个种子想法，但需要帮助将其发展成完整概念。
- 请他们分享模糊的想法 — 哪怕几个字就够了
- 确认这是一个好的起点（不要评判或改变方向）
- 建议运行
/brainstorm [他们的线索]来发展它 - 展示推荐路径：
/brainstorm [线索]— 将想法发展为完整概念/setup-engine— 配置引擎/map-systems— 将概念拆解为系统并规划 GDD 编写顺序/prototype— 测试核心机制/sprint-plan— 规划第一个冲刺
如果选 C：清晰的概念
用户知道自己要做什么，但还没有形成文档。
- 提出 2-3 个后续问题来了解他们的概念：
- 类型和核心机制是什么？（一句话）
- 有引擎偏好吗，还是需要帮助选择？
- 大致规模如何？（Game Jam 游戏、小型项目、大型项目）
- 根据他们的回答，提供两条路径：
- 先正式化：运行
/brainstorm，将概念结构化为正式的游戏概念文档，包含游戏支柱（Pillars）、MDA 分析和规模层级 - 直接配置引擎：如果用户对概念很有信心，直接进入
/setup-engine，之后手动编写 GDD
- 先正式化：运行
- 展示推荐路径（根据他们的选择调整）：
/brainstorm或/setup-engine（由用户选择）/design-review— 验证概念文档/map-systems— 将概念拆解为独立系统，标记依赖关系和优先级/design-system— 编写各系统的 GDD（引导式，逐节完成）/architecture-decision— 做出第一批技术决策/sprint-plan— 规划第一个冲刺
如果选 D：已有成果
用户已经有工件了。弄清楚什么存在、什么缺失。
- 分享你在步骤 1 中的发现（现在它相关了）：
- "我看到你有 [X 个源文件 / Y 份设计文档 / Z 个原型]..."
- "你的引擎 [已配置为 X / 尚未配置]..."
- 建议运行
/project-stage-detect进行全面分析 - 如果引擎未配置，指出应先运行
/setup-engine - 展示推荐路径：
/project-stage-detect— 全面的缺口分析/setup-engine— 如果尚未配置/design-system— 如果系统索引存在但 GDD 不完整/gate-check— 验证是否准备好进入下一阶段/sprint-plan— 整理工作
4. 继续前确认
在展示推荐路径后，询问用户想先执行哪一步。永远不要自动运行下一个技能。
"你想从 [推荐的第一步] 开始，还是想先做其他事情？"
5. 交接
当用户选择下一步时，让他们自己调用技能，或者主动提出帮他们运行。无论哪种方式，一旦用户有了明确的下一步行动，/start 技能的任务就完成了。
边界情况
- 用户选了 D 但项目为空：温和地引导 — "看起来项目是一个全新模板，还没有任何工件。路径 A 或 B 可能更合适？"
- 用户选了 A 但项目中有代码：提及你的发现 — "我注意到
src/中已有代码。你是想选 D（已有成果）吗？还是想用新概念重新开始？" - 用户是回访者（引擎已配置、概念已存在）：完全跳过入门 — "看起来你已经配置好了！引擎是 [X]，游戏概念在
design/gdd/game-concept.md。想从上次停下的地方继续吗？试试/sprint-plan，或者直接告诉我你想做什么。" - 用户不属于任何选项：让他们用自己的话描述情况，然后灵活适配。4 个选项是起点，不是牢笼。
协作协议
此技能遵循协作设计原则：
- 先询问 — 永远不要假设用户的状态或意图
- 展示选项 — 给出清晰的路径，而非命令
- 用户决定 — 由他们选择方向
- 不自动执行 — 推荐下一个技能，但不要未经询问就运行
- 灵活适配 — 如果用户的情况不符合模板，倾听并调整
© 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/start of pixel-cellar/Claude-Code-Game-Studios.
Open the folder on GitHubat commit 2c016ef
More from pixel-cellar/Claude-Code-Game-Studios
All 23 skills in this repoSetup Engine
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。
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.
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.
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.
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.
Questions about Start
What does Start do?
首次入门引导 — 询问你当前处于哪个阶段，然后引导你进入正确的工作流。不做任何假设. An agent skill from pixel-cellar/Claude-Code-Game-Studios. Start is an agent skill from pixel-cellar/Claude-Code-Game-Studios.
How do I install Start in Claude Code?
Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a claude-code`. Or copy the skill folder (.claude/skills/start in pixel-cellar/Claude-Code-Game-Studios) into .claude/skills/start in your project. Claude Code loads it when a task matches its description.
How do I install Start in Codex?
Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill start -a codex`. Or copy the skill folder (.claude/skills/start in pixel-cellar/Claude-Code-Game-Studios) into .agents/skills/start in your project. Codex loads it when a task matches its description.
Can I use Start 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 start -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/start, .gemini/skills/start, .github/skills/start and .opencode/skills/start in your project.
What does Start need to run?
SKILL.md names no scripts, command-line tools or credentials: Start is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, AskUserQuestion.
Does Start 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 Start 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 Start use?
Start 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 Start use?
About 886 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Who maintains Start?
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.