Design game experience, systems, and levels. Converge the chosen concept into one GAME_DESIGN defining the player promise, core loop, how the world responds, the systems actually needed, level pacing, feedback, failure, and a fully playable prototype. Use for design the game world, deepen the gameplay and levels, write the game design document. 游戏体验、系统与关卡策划。把选定概念收束为一份 GAME_DESIGN,定义玩家承诺、核心循环、世界响应、必要系统、关卡节奏、反馈、失败和可完整游玩的原型。用于设计游戏世界、深化玩法和关卡等需求。
npx skills add https://github.com/worldwonderer/novel-to-game --skill game-world-design
把选定概念变成可实现的玩家体验,不写世界观百科或工程方案。
读取 world-design-method.md;定资源、门槛与难度时同读 numeric-design-method.md。输入必须包含
SOURCE_BIBLE.md、已选择的 CONCEPT.md 和 PRODUCT_BRIEF.md。
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。
失败与恢复;不要照搬其他类型的字段。
(默认 10-30 分钟,不超过 PRODUCT_BRIEF 单局时长,范围沿用概念卡界定的切片),每拍
都写玩家已知、引入的新压力和可观察反馈,而非写“丰富内容”;冷启动脚本、张力目标等
每拍细则见 world-design-method.md 关卡节奏节。
10. 列出明确非目标、验收条件,以及未读策划的玩家应通过试玩理解什么。
11. 按 PRODUCT_BRIEF 的玩家结构写明切片的社交表现假设(纯单人 / 单人 + AI 假多人 /
单人 + 占位异步榜),并以受众画像为决策密度、UI 密度与教学强度的标尺校准关卡节拍。
12. 明确首发界面语言和本地化范围;玩家可见文案、术语、阅读顺序、字体和文本长度
必须适配目标语言与文化,不因翻译破坏信息层级或玩法可读性。
13. 定文案声口:按题材、目标市场和分级选定玩家可见文本的调子,并把去AI味标准写进设计,
供构建阶段照办。见 game-writing-craft.md。文案是核心
体验面,不是收尾附属。
14. 标注角色内容层级与升级门;支持短线至少有一次真实选择、持久态度和下游回响,未经试玩
证据不静默升级为核心路线。
非玩家角色、势力和事件只设计到玩家能够感知和影响的深度。GAME_DESIGN 不得出现文件名、
函数名、存储键、测试脚本名;确定性与持久化写成规则需求(如同种子同指令同结果、存档跨
周目保留哪些状态),实现参数、类结构、着色器、资产管线与实现符号由构建阶段的
BUILD_BRIEF 决定。
生成一个 design/GAME_DESIGN.md。必需节 checklist 如下,每行是节名加验收判据:
同玩法先例,并逐条列出共有的那 3-5 个核心动词(BUILD_BRIEF「同玩法动词清单」逐字
抄这几行,QA 逐个动词要证据);本作的独有之处落在这些动词作用于什么、代价与世界回应,
不落在动词本身。
文本**,并指明各自出现在哪一屏。这不是把核心幻想抄一遍:brief 的措辞是写给团队的,
这里要的是屏幕上的句子。风格锁了「无教程 / 纯 diegetic」也要写——那约束的是用什么
手段说,不是可以不说。
一个可观察的结束标记(第几夜 / 第几关 / 某事件)。相邻两期差集为空即不成立;新内容、
计数器与等级读数不算差集。
(一次性知识 / 可再生判断)。
字段附「消费点」列,至少一个规则读取点(选项门槛 / 事件触发 / 结局条件),供 QA 按
只写不读审计。
达到每档门槛的最少动作数,并演算一条及格线路径,证明最高档在切片预算内可达但需
多次正确选择。
10. 决策深度示例——一个代表性决策点 × 3-5 个可选动作 × 至少 2 个状态取值的真实数值表,
状态维度取自玩家 HUD 可见变量,标注最优动作在哪个取值处翻转。
11. 品类保真 go/no-go 表——四问各占一行,填 go/no-go 并附一句实现可验证的证据描述
(如“敌方单体技优先攻击被自己克制的我方单位”):
① 世界 / 对手是否也在用核心系统对玩家出招(敌人用相克、女主用嫉妒与索取);
② 每个非教学回合 / 节拍是否存在真选择(无通吃动作,选项后果可区分);
③ 签名幻想是否落在可重复核心动词而非过场 / 道具;
④ 作为卖点的核心系统是否提供非被支配选项(每条策略在某个局面下最优)。
12. 关卡节拍——教会/变式/组合/检验/命运回收五拍齐全;教会拍含冷启动 / 前 60 秒脚本,
检验拍含绑定基准策略脚本的可测张力目标。
13. 首屏焦点与披露状态表——第一帧唯一焦点、次级面板初始态与揭示触发,定义见
world-design-method.md 同名节。
14. 反馈与失败——失败显示发生了什么和玩家下次能改变什么。
15. 社交表现假设——与 PRODUCT_BRIEF 玩家结构一致,供构建与 QA 消费。
16. 最小试玩问题、范围与非目标、验收和最小游玩验证——试玩问题针对最大设计假设。
17. 角色内容层级与升级门——短线未经试玩证据不升级为核心路线。
18. 受众、文化与语言范围,文案声口与去AI味标准。
规则用短表格表达,不再复制为 JSON。
完成前确认(任一为否就回去改,不算分):
加量;删除支持系统后核心循环仍成立。
有东西在复利,成熟期玩家做得到新手做不到的事。新解锁的内容(新文本、新场景、新
收集物)不算差集,计数器、等级与熟练度读数变大也不算;差集必须是玩家能做的事变了。
每期在正式流程里要有一个可观察的结束标记(第几夜 / 第几关 / 某个事件),QA 据此停表。
别等 build 后返工。
输出交回总入口,不自行推进美术或构建阶段。
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
> This skill orchestrates autonomous discovery of brand materials across enterprise platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, Slack). It should be used when the user asks to "discover brand materials", "find brand documents", "search for brand guidelines", "audit brand content", "what brand materials do we have", "find our style guide", "where are our brand docs", "do we have a style guide", "discover brand voice", "brand content audit", or "find brand assets".
Low-level Python plotting for scientific figures: publication-quality line, scatter, bar, heatmap, contour, 3D; multi-panel layouts; fine control of every element. PNG/PDF/SVG export. Use seaborn for quick stats, plotly for interactive.
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
Enterprise-grade PowerPoint deck generation system using evidence-based prompting techniques, workflow enforcement, and constraint-based design. Use when creating professional presentations (board decks, reports, analyses) requiring consistent visual quality, accessibility compliance, and integration of complex data from multiple sources. Implements html2pptx workflow with spatial layout optimization, validation gates, and multi-chat architecture for 30+ slide decks.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an HTML slide deck and asks to compare/audit/verify/fix the export — including phrases like "compare ppt with html", "fidelity audit", "fix the pptx", "ppt is cut off", "footer overlap", "italic missing in pptx", "re-export the deck", "pptx-html-fidelity-audit", or any case where a python-pptx → HTML round-trip needs verification or repair. Also trigger when the user shows you a deck.html and a deck.pptx side by side and is debugging visual differences.
Take worldwonderer/game-world-design from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.