zenstory-ai/novel-to-game / skills/game-design
game-design
VerifiedChoose a playable gameplay concept, design world rules, systems, levels, and branching narrative, and set visual and audio direction. Turns SOURCE_BIBLE and PRODUCT_BRIEF into separate CONCEPT, GAME_DESIGN, and ART_DIRECTION specs stage by stage without writing code. Use when deciding what game a novel should become, comparing gameplay directions, writing a game design spec, designing branching story or interactive film scenes, or setting art direction. 游戏策划与美术方向:基于 SOURCE_BIBLE 与 PRODUCT_BRIEF 分阶段产出玩法选型(CONCEPT)、世界与叙事设计(GAME_DESIGN)及美术视听方案(ART_DIRECTION),覆盖改编方向比选、系统与关卡设计、互动叙事与影游分镜、视觉与音效定调。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.0 KB |
| agents/openai.yaml | config | 321 B |
| references/art-direction-method.md | markdown | 3.3 KB |
| references/concept-method.md | markdown | 3.2 KB |
| references/interactive-film-method.md | markdown | 3.7 KB |
| references/narrative-design-method.md | markdown | 2.4 KB |
| references/world-design-method.md | markdown | 3.5 KB |
references/narrative-design-method.md
View on GitHub# 互动叙事的改编边界
以场景推进、人物交锋、信息差或关键抉择为核心玩法时使用。行文贴合原著的语体、称谓、人物口吻与文化概念,跨语种改编时不套异域套路。
## 场景与人物
只记真正影响玩法与实现的场景因果:在场人物的盘算与筹码、玩家可介入的节点、知情边界、离场时的状态变化及对后文的回响;不给每场戏硬套统一字段模板、固定节拍或台词字数。对白和选项必须是角色按身份、处境与已知信息真会说出口、做出来的事,不把作者的事后评判或结局剧透塞进选项。场次可以合并压缩,但不能为赶进度让人物做出违背自身动机与筹码的举动。
## 知情与证据
秘密、证词与误判按「客观真相、人物已知或误信、玩家已获知」三层分开记。每件证据分清具体证物或字据、它能直接坐实的最小结论,以及仍待查证的推论。新线索可以推翻对旧证据的解读,不能涂改已经发生过的事实;所有角色一律只按自己当下知晓的信息行事。未揭晓的秘密不仅对白里不能漏嘴,物品名称与说明、章节标题、人物头衔和同场站位也一并守口如瓶。
原著里的重生、预知、系统面板或神通,严格沿用书里立下的触发条件、知情范围与代价,不在人物遇困时临时开挂扩权。
## 选择后果与分支汇流
关键选择记下玩家的实际言行、当场人物反应、留下的既成事实及后文呼应处,不用一条隐藏好感总分抹平具体恩怨。个人线的核心抉择紧扣该角色自身的心结与算盘,不写成对谁都管用的场面讨好话;亲疏变化优先借神情、称呼改口、允许出入的院落与肯托付的私事表现,少靠加减数字交代。
不同分支可以在公共场次汇流,但汇流后的台词、在手器物、人物关系与可选动作必须贴合玩家走过的路径,不把未选分支发生的事当成既成事实;汇流点逐项核对关键物件在谁手里、各人何时到场与离席。只保留后文真会读取的状态标记;承诺、证词、器物去向与当众表态都要在当事人反应或后续局面里有所交代。定稿前取代表性路径正反走读一遍:无人未卜先知,无未选分支串词,每个结局都能追溯到玩家先前的具体选择。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |