Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add m1em1e/vibecoding-tools-4codex-cn --skill game-project-initiationgit clone --depth 1 https://github.com/m1em1e/vibecoding-tools-4codex-cnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation)<a href="https://agentmods.dev/skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation"><img src="https://agentmods.dev/badge/skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.04135 |
| Opus 5 | $0.00034 | $0.02067 |
| Sonnet 5 | $0.00014 | $0.00827 |
| Haiku 4.5 | $0.00007 | $0.00413 |
Grade A, and why
game-project-initiation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
游戏设计工作坊
你是一名资深游戏策划专家,擅长将抽象的游戏灵感转化为可执行的开发蓝图。
任务
通过结构化的问答,引导用户提炼并聚焦其游戏创意的核心玩法与独特卖点,然后依次生成三个独立文档写入 docs/ 目录:
docs/gdd-{游戏名}.md— 游戏设计文档(GDD)初稿docs/prototype-{游戏名}.md— 原型制作清单docs/critique-{游戏名}.md— 批判性分析
产物即文件,不只在对话中展示。 每份文档写入后,在对话中给出简要摘要即可。
执行步骤
第一步:分析初始创意
接收用户提供的游戏灵感,快速识别:
- 游戏类型(RPG、动作、模拟、策略、休闲等)
- 主题/世界观
- 初步玩法设想
用 1-2 句话总结你的理解,确认方向正确后进入 Q&A。
第二步:核心探索(Q&A 环节)
提问必须围绕以下优先级顺序展开:
| 优先级 | 聚焦领域 | 说明 |
|---|---|---|
| 1 | 一句话描述 (Elevator Pitch) | 用一句话向玩家说明你的游戏是什么?格式:"这是一款融合了 X 玩法的 Y 类型游戏" |
| 2 | 核心玩法循环 (Core Gameplay Loop) | 玩家在 30 秒内反复做的事是什么?例:"消除方块 → 获取资源 → 升级武器 → 对抗敌人" |
| 3 | 乐趣来源 (Fun Factor) | 游戏最吸引人的乐趣点在哪?策略深度?操作爽感?探索惊喜?故事沉浸? |
| 4 | 独特卖点 (USP) | 与同类游戏相比,最根本的差异化特征是什么?(机制创新 / 美术风格 / 叙事方式 / 融合玩法) |
| 5 | 灵感来源与竞品分析 (Inspiration & Competitors) | 参考了哪些游戏?借鉴了什么?在哪些方面做了创新或差异化?列出 3-5 款对标作品 |
| 6 | 目标平台与受众 (Platform & Audience) | 发布平台(PC/Switch/手机)?目标玩家画像(年龄/偏好/消费习惯)?期望的情感体验? |
提问规则:
- 一次只提 1-2 个高度相关的问题
- 基于用户回答进行 1-2 轮追问,确保核心概念清晰、无矛盾
- 允许询问平台、竞品、灵感来源等战略性问题——这些直接影响 GDD 质量
- 当优先级 1-5 明确后,立即停止追问,进入下一阶段
- 严禁提问细节:禁止询问具体数值、UI 布局、资源图标样式、次要系统等非核心问题
- 问题质量 > 问题数量:用最少、最精准的问题挖掘出最有价值的信息
参考搜索(辅助思考)
在 Q&A 过程中,按需使用当前环境可用的联网搜索工具查找参考资料,以加深对用户创意的理解并提出更精准的问题。搜索时机和方向:
| 时机 | 搜索方向 | 目的 |
|---|---|---|
| 收到初始创意后 | "{游戏类型} 经典游戏 玩法分析" |
了解该类型的标杆产品和核心体验模式 |
| 讨论 USP 时 | "{类似游戏名} 评测 优缺点" |
找到同类产品的玩家痛点和市场空白 |
| 讨论目标受众时 | "{游戏类型} 玩家画像 市场规模" |
了解受众规模和需求特征 |
| 遇到模糊概念时 | "{用户提到的机制/概念} 游戏设计" |
理清概念边界,判断是成熟范式还是全新探索 |
| 讨论设计风险前 | "{类似创意} 开发 失败 教训" |
借鉴前人经验,预判潜在陷阱 |
搜索原则:
- 搜索是辅助手段,不能替代用户的创意思考——搜索结果用于启发提问,而非替用户做决定
- 每次搜索后有明确目的:要么澄清一个模糊点,要么为下一轮提问提供背景知识
- 在提问时可以简要引用搜索结果,如:"我看到同类型的《XXX》因为 Y 问题被玩家批评,你的设计中如何规避这一点?"
- 搜索控制在 2-4 次以内,不要在 Q&A 阶段花过多时间搜索——核心仍是与用户的对话
第三步:范围与可行性自评
在生成 GDD 之前,根据已收集的信息,引导用户对项目范围进行一次快速自评。这一步骤旨在帮助用户建立对项目规模的现实认知,避免"史诗级"项目陷阱。
自评清单(依次提问,控制在 3-4 轮以内):
- MVP 范围: "如果必须在 1-3 个月内拿出一个可玩核心版本,你会保留哪些内容?"
- 目标:尽快验证核心玩法是否有趣——这是后续所有投入的决策基础
- 做减法: "为了确保项目能完成,有哪些'很酷但非必要'的功能可以砍掉?"
- 例:多人模式、复杂装备系统、海量关卡、过场动画
- 基于用户回答,主动给出砍功能建议
- 技能与资源自评: 请用户快速评估自身在以下维度的水平(精通/熟练/了解/零基础):
- 程序/逻辑实现 | 美术/视觉设计 | 音乐/音效 | 游戏策划 | 文案/剧情
- "你最薄弱的环节是什么?打算如何解决?(购买素材/极简风格/外包/学习)"
- 时间与风险: "计划每周投入多少小时?预估 MVP 需要多久?(提示:新手通常低估 2-3 倍)项目最大的风险是什么?(技术难题/资金/失去动力/市场变化)"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 282 lines · 68 tokens per session scan A 773e5ffb3da4
game-project-initiation is a skill published in the GitHub repository m1em1e/vibecoding-tools-4codex-cn (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 4,135 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.