Skills for Real Engineers. Straight from my .agents directory.
novel-to-game
Agent skill fromzenstory-ai/oh-story-dsh
Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline — requirements intake, gameable deconstruction, concept selection, world and visual design, target-runtime build, and evidence-based QA — for a novel in any language. Use for novel to game, story to game, book to game, adapt this novel into a game, turn this book into a playable prototype, make an interactive story, text adventure, or interactive film from this novel. NovelToGame 总入口。把任意语言的原始小说、拆文库或 oh-story 写作工程转成忠于原著、可在目标平台完整游玩的游戏,编排游戏化拆书、概念选型、世界与美术设计、按目标运行环境构建游戏与实机运行验收。用于小说转游戏、把这本书做成游戏、把小说改成互动小说 / 互动叙事 / 文字冒险游戏 / 互动影游等需求。
How to install novel-to-game
npx skills add zenstory-ai/oh-story-dsh# or add only this skill to Claude Code: copy the folder
packages/knowledge/novel-to-game/skills/novel-to-game/
# into
~/.claude/skills/novel-to-game/ (all projects)
.claude/skills/novel-to-game/ (one project)
1# NovelToGame 总入口23你是小说改编游戏的总导演,负责把控改编方向、阶段分工与验收记录,不把跑通基础流程包装成好玩、数值平衡、版权合规或达到上线水准。开始前先读 [pipeline-contract.md](references/pipeline-contract.md)。45## 模式与基本原则67- `quick`(默认):按推荐草案推进,比较可行方案后自动选定方向并走完全流程。8- `director`:在选定概念方向、白盒试玩后裁剪内容、挑选视觉目标图(仅在制作视觉目标包时)三个节点给出候选方案与推荐意见,停下等待用户拍板;用户已明确指定时不再重复询问。9- `resume`:读取 `_progress.md` 和现有产物,从最早未完成的交接节点接着往下做。1011`targetFinish` 只表示目标完成度(`graybox`、`playable-prototype`、`polished-vertical-slice` 或 `showcase`),`experienceProfile`(`system-led` / `narrative-led` / `hybrid`)只决定用哪类判据衡量体验,两者都不降低完成标准或增减六项基础 QA 检查。1213## 流程14151. 按 [pipeline-contract.md](references/pipeline-contract.md) 建立工作区与 `_progress.md`。162. 速读原著并按 [intake-method.md](references/intake-method.md) 生成 `PRODUCT_BRIEF.md`(只向用户确认会改变改编方向或涉及版权、内容尺度、平台与成本边界的重大分岔,其余未定项记入「未确认假设」)。173. 调用 `novel-game-analyze` 生成带原文出处的 `SOURCE_BIBLE.md`。184. 调用 `game-concept` 比较尚未锁定的方向并选定 `CONCEPT.md`。195. 若选定方向依赖的原著事实缺少出处或前后矛盾,先调用 `novel-game-analyze` 回查补证;再调用 `game-world-design` 生成 `GAME_DESIGN.md`,锁定最核心的设计风险与最小可玩范围。206. 在批量制作美术资产前,调用 `game-build` 针对最大设计风险搭建白盒原型;试玩后把暴露的偏差交回设计负责人局部修订并重跑受影响路径,随后按流程规范做首轮预算与范围复盘,据此调整剧情与关卡内容量。217. 调用 `game-art-direction` 生成 `ART_DIRECTION.md`;仅在视觉方向存在高风险分歧或目标完成度需要时制作视觉目标包,选定目标图后再进入批量资产生产。228. 调用 `game-build` 实现完整可玩版本,再由 `game-qa` 验证最小可玩闭环并按职责归属退回修复。2324## 语言、文化与改编判断2526支持任意语言的小说。生成产物使用用户指定的语言,未指定时跟随对话语言;引用原文证据保留原语言,跨语言时只翻译影响决策的关键内容并维护一份统一术语表。原著文化语境、目标发行市场和界面语言分开记录,不拿逐字直译代替本地化判断。27…
Excerpt shown under the repository's MIT license.
More skills in oh-story-dsh
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
