game-project-initiation

game-project-initiation is a skill for Claude Code, Codex from m1em1e/vibecoding-tools-4codex-cn. It costs 68 tokens per session (4,135 once invoked), scanned A, original, MIT.

A guided game-design workshop that turns a game idea into an initial design plan. It asks structured questions, then creates a game design document, a prototype checklist, and a critical analysis.

In plain words
What is it for?
It is for shaping a new game concept, checking its scope, and producing planning documents in the project’s docs folder.
Why use it?
Early game ideas are often too broad or unclear to build. The workshop helps define the main gameplay, audience, platform, inspiration, and differences from similar games.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It is for shaping a new game concept, checking its scope, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation
Install

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.

Any agent
npx skills add m1em1e/vibecoding-tools-4codex-cn --skill game-project-initiation
Clone the repo
git clone --depth 1 https://github.com/m1em1e/vibecoding-tools-4codex-cn

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for game-project-initiation

README.md
[![agentmods](https://agentmods.dev/badge/skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation.svg)](https://agentmods.dev/skills/m1em1e/vibecoding-tools-4codex-cn/game-project-initiation)
Your own site
<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>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 773e5ffb3da4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

skills/game-project-initiation/SKILL.md · 282 lines

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:

  1. docs/gdd-{游戏名}.md — 游戏设计文档(GDD)初稿
  2. docs/prototype-{游戏名}.md — 原型制作清单
  3. 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):

  1. 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
  2. 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
  3. 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)"
  4. 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)"

Read the full file on GitHub · 282 lines

Changes

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.

  1. 6d ago First seen · 282 lines · 68 tokens per session scan A 773e5ffb3da4

Subscribe to this mod's changes

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.