Agent skill · Design & Presentation

game-concept

Design game concepts from a novel. From SOURCE_BIBLE and PRODUCT_BRIEF, generate three genuinely different directions on the dimensions still unlocked, then pick the most worthwhile playable prototype using hard vetoes and explicit trade-offs. Use for what game should this novel become, compare game concepts, choose a game direction for this book. 小说游戏概念设计。根据 SOURCE_BIBLE 与 PRODUCT_BRIEF 在未锁定维度上生成三个真正不同的方案,用硬否决和关键取舍选择最值得做的可玩原型。用于判断小说适合做成什么游戏、比较游戏方案等需求。

pitechen592★ · +23/wk · 2 repos on radarProfile →
claude-codecodexMIT
Install
npx skills add worldwonderer/novel-to-game --skill game-concept --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/game-concept/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 555
Language: Markdown

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 游戏概念设计 决定做成什么游戏,不写代码或功能愿望清单。 读取 [concept-method.md](references/concept-method.md)。输入必须包含 `SOURCE_BIBLE.md` 与 `PRODUCT_BRIEF.md`;缺 `SOURCE_BIBLE` 就停止并说明缺游戏化拆解,缺 `PRODUCT_BRIEF` 就停止 并要求先过需求 intake,不代替总入口推进其他阶段。 产物语言由 `PRODUCT_BRIEF.md` 锁定;未锁定时跟随对话语言,不默认产出中文。 ## 行业锚定 产品框架以 `PRODUCT_BRIEF.md` 记录的全部产品维度为准,intake 阶段已锁定,**直接继承, 不重猜、不静默改**;记 N/A 的维度也是锁定值,不自行补默认。受众画像(硬核度 / 性别向 / 玩家动机原型)是决策密度、UI 密度、单局时长与教学强度的标尺,本阶段继承并落地,不在 概念里另起一套。本阶段只在这个框架内把它落成一页可指导取舍的产品定义:玩家是谁、在 既定主类型下的具体子类型、3 条体验支柱、明确非目标和最大未知。体验支柱必须能指导 取舍,例如“预读后改写敌方结果”,不能写“沉浸、史诗、精致”。每条支柱都要配一个可观察 的试玩证据和一个会否决它的失败现象。若发现 `PRODUCT_BRIEF` 的某项与原作适配明显冲突, 回总入口显式修订,不在本阶段擅自更改。 `PRODUCT_BRIEF` 已按"小说语言→对标市场"锁定对标方向与几款参考对标,本阶段以那几款为 起点做 per-direction 深化验证,不推翻已定市场重新来过。整个概念阶段只保留 2-4 款真正 解决过相近设计问题的核心对标,再加一个必要的市场同类或反例。对标事实须先联网核实并在 对标矩阵标注核实状态,方法见 concept-method.md。 玩法取自已被大量玩家玩过的成熟打法,小说只做 IP 皮:创新落在世界、人物、剧情、题材与 美术,不落在动词集。选定方向必须有 **≥2 款「同玩法」对标**——核心动词与循环结构就是 它们那一套——并逐条列出共有项;凑不出就换打法,不靠文学契合度豁免。 对标组合必须同时覆盖玩法问题和文化市场问题:研究原作文化中的题材表达,也研究目标 语言市场的玩家预期、类型惯例、内容敏感点和传播语境。一款游戏可以同时承担两种证据, 不为地域凑名单。区分可迁移的玩法原则与不可照搬的文化符号、笑点、价值关系和商业惯例。 每个核心对标必须回答: - 借用层级是「同玩法」还是「仅原则」;标同玩法的,逐条列出共有的核心动词与循环结构, 并附一条可核实的“玩过的人很多”凭据——**一个带来源与日期的数字**(商店评价数 / 峰值同时 在线 / 公布销量或注册数);“有商店页或维基页”只证明这游戏存在过,不算凭据,列

What's inside
Steps it walks through
  1. 行业锚定
  2. 三个方向
  3. 选择
  4. 输出
Ships with 2 files
  • agents/openai.yaml
  • references/concept-method.md
More from novel-to-game
All skills →
About this skill
What does the game-concept skill do?

Design game concepts from a novel. From SOURCE_BIBLE and PRODUCT_BRIEF, generate three genuinely different directions on the dimensions still unlocked, then pick the most worthwhile playable prototype using hard vetoes and explicit trade-offs. Use for what game should this novel become, compare game concepts, choose a game direction for this book. 小说游戏概念设计。根据 SOURCE_BIBLE 与 PRODUCT_BRIEF 在未锁定维度上生成三个真正不同的方案,用硬否决和关键取舍选择最值得做的可玩原型。用于判断小说适合做成什么游戏、比较游戏方案等需求。

How do I install it?

Run `npx skills add worldwonderer/novel-to-game --skill game-concept --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From worldwonderer/novel-to-game, a repository with 555 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going