Agent skill

Novel-to-Game Concept Design

by zenstory-ai in zenstory-ai/novel-to-game

Compares game concepts for adapting a novel, rules out weak ones with hard vetoes and writes the chosen playable direction to a CONCEPT.md file.

MITAuto-check passedGame Development

SKILL.md written in Chinese; this summary is our English description.

Install Novel-to-Game Concept Design

skills CLI
$ npx skills add zenstory-ai/novel-to-game --skill game-concept -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zenstory-ai/novel-to-game game-concept --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/game-concept .claude/skills/game-concept && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
game-concept
GitHub stars
841
Token cost
~423 tokens
SKILL.md length
66 words
Files
3 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Compares game concepts for adapting a novel, rules out weak ones with hard vetoes and writes the chosen playable direction to a CONCEPT.md file.

  • Works in 7 steps: brief 锁定值与开放维度; → 体验承诺及其可观察现象和失败现象; → 紧凑先例说明; → …
  • Deciding what game a novel could become
  • SKILL.md covers 决策边界, 比较范围, 选择 and 输出
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill decides what kind of game a novel should become. It writes no code, balance tables or level scripts. It needs `SOURCE_BIBLE.md` and `PRODUCT_BRIEF.md` as input and stops with a note about the gap if either is missing, rather than inventing the upstream material. Values the brief has locked, such as platform, audience, rating, length and target market, are inherited as they are.

Only dimensions that are still open get compared, and only directions that show a real trade-off. Candidates are eliminated by the hard vetoes in `references/concept-method.md`, without adding up scores. In `quick` mode the skill picks the direction with the strongest evidence; in `director` mode it recommends one and waits for you. The result is `concepts/CONCEPT.md`, with the experience promise, candidate concept cards, veto results, trade-offs, the player agency contract and the smallest validation questions. Interactive narrative is treated as a full game form.

When your agent uses it

  • Deciding what game a novel could become
  • Comparing candidate game directions for a book adaptation
  • Judging whether a novel suits an interactive story

Example prompts

  • “Compare game concepts for my fantasy novel using SOURCE_BIBLE.md and PRODUCT_BRIEF.md.”
  • “Pick a playable direction for this book, in director mode so I make the final choice.”
  • “Decide whether this novel should become an interactive story or a different kind of game.”

Requirements

  • SOURCE_BIBLE.md and PRODUCT_BRIEF.md in the project

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. brief 锁定值与开放维度;
  2. 体验承诺及其可观察现象和失败现象;
  3. 紧凑先例说明;
  4. 候选概念卡:主类型、experienceProfile、借用/拒绝的玩法先例、核心动作与循环、压力、失败、
  5. 硬否决结果、关键取舍、推荐与选择状态;
  6. 选定方向的玩家能动性合同、不可妥协体验承诺;
  7. 最小验证问题与开放问题。

What it can do on your machine

Read from SKILL.md and the folder at commit 03feee9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel-to-Game Concept Design loads about 423 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 66 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~423
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zenstory-ai/novel-to-game at commit 03feee9, republished under its MIT licence (© zenstory-ai). 66 words, ~423 tokens.

Download SKILL.mdSave it as .claude/skills/game-concept/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
game-concept
description
Design game concepts from a novel. From SOURCE_BIBLE and PRODUCT_BRIEF, compare meaningful alternatives on the dimensions still unlocked, then select a playable direction 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, decide whether this novel should become an interactive story. 小说游戏概念设计。根据 SOURCE_BIBLE 与 PRODUCT_BRIEF 比较未锁定维度上的有效替代方案,用硬否决和关键取舍选择可玩方向。用于判断小说适合做成什么游戏、该不该做成互动叙事、比较游戏方案等需求。

游戏概念设计

决定做成什么游戏,不写代码、数值表或逐场关卡脚本。

读取 concept-method.md。输入必须包含 SOURCE_BIBLE.md 与 PRODUCT_BRIEF.md;缺任一项就停止并说明缺口,不代替上游补写。

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。

决策边界

直接继承 brief 已锁的平台、输入、受众、分级、时长、目标市场和非目标;发现它们与原作明显冲突 时回总入口修订,不在概念阶段静默改值。原作语言、文化语境、目标市场和界面语言分别处理,不从 其中一个自动推出另一个。

互动叙事是成熟玩法,不因以阅读和对白承载就降低标准;它的动词可以是读局面、追问、比对信息、 表态、隐瞒、交出与承担回响。

概念还要判断验证形态:可用成熟交互语法表达时说明“已有语法 + 原作如何改变它”;核心依赖实时手感、 空间、视线、物理或独特操作时明确走自定义灰盒。不要把文本原型当所有体验的统一前置层,也不要因有 模板可用就让模板替原作决定玩法。

比较范围

先列 brief 的锁定维度和仍开放的维度,只比较能揭示真实取舍的方向,不凑概念数量或差异维度。 仅在方向仍开放时考察可信替代;用户已选定方向或不存在有效替代时说明原因,改为验证该方向的风险, 不重开选择。

选择

先按 concept-method 的硬否决逐个淘汰,不计算总分,再按其比较维度选择。quick 自动选证据最强的 方向;director 只对尚未决定的方向给出推荐并等待用户选择。

输出

生成一个 concepts/CONCEPT.md,只含:

  1. brief 锁定值与开放维度;
  2. 体验承诺及其可观察现象和失败现象;
  3. 紧凑先例说明;
  4. 候选概念卡:主类型、experienceProfile、借用/拒绝的玩法先例、核心动作与循环、压力、失败、 世界响应;说明玩家身份如何形成反复行动、执行阻力与可观察变化,不要求独立的固定键名。 signature_command 按方法「身份专属命令」写值或 N/A;最后说明原作张力如何由玩家亲手 enact、 招牌画面、最小验证切片、最大风险和否决观察;
  5. 硬否决结果、关键取舍、推荐与选择状态;
  6. 选定方向的玩家能动性合同、不可妥协体验承诺;
  7. 最小验证问题与开放问题。

narrative-led 或 hybrid 的叙事层还要选择一种分支结构语法并说明内容预算。交接前确认选定方向 可在 brief 范围内做成完整切片。

© zenstory-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/game-concept of zenstory-ai/novel-to-game.

  • SKILL.md
  • agents/openai.yaml
  • references/concept-method.md

Open the folder on GitHubat commit 03feee9

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in zenstory-ai/novel-to-game, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Novel-to-Game Concept Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel-to-Game Concept Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel-to-Game Concept Design this skillzenstory-ai/novel-to-game841—~423Automated safety check: PassMIT
Interactive Film AuthoringNarcooo/inkos10k—~774Automated safety check: PassAGPL-3.0
InkOS Interactive World PlayNarcooo/inkos10k—~793Automated safety check: PassAGPL-3.0
Game Designericrisco/rsc-harness180—~3.6kAutomated safety check: PassMIT
Game Design Book TranslatorDY-2026/GameDesignOS415—~744Automated safety check: PassMIT
Environment Artistarjun988/blender-skills283—~1.2kAutomated safety check: PassMIT

Similar skills

  • Method for writing interactive film and game scripts with branching story trees, state variables, producible nodes, multiple endings and consistent assets.

    10k GitHub stars~774 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Rules for advancing an interactive story or open world in an InkOS Play session: honor the world contract, finish actions, keep state and time consistent.

    10k GitHub stars~793 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Game Design

    ericrisco/rsc-harness

    A skill your agent uses when designing or repairing what makes a game fun — verbs and mechanics, moment-to-moment/session/meta loops, progression, economy faucets and sinks, difficulty curves…

    180 GitHub stars~3.6k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Game Design Book Translator

    DY-2026/GameDesignOS

    用于翻译、润色、整理或质检英文游戏设计、游戏研发、系统设计、UX、Game Studies 与设计理论书籍、章节、PDF、OCR、Markdown、图表、图注和术语表;强调专业术语、中文可读性、图片结构与版权边界。Use for professional game-design translation and QA.

    415 GitHub stars~744 tokensUpdated 1 mo ago
    Game DevelopmentAuto-check passed
  • Environment Artist

    arjun988/blender-skills

    AAA environment art for modular kits, buildings, terrain, vegetation, architecture, and scene composition.

    283 GitHub stars~1.2k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Data Storytelling

    ynulihao/AgentSkillOS

    Transform data into compelling narratives using visualization, context, and persuasive structure.

    618 GitHub starsUsed in 15 repos~2.8k tokens
    Writing & ContentAuto-check passed

More from zenstory-ai/novel-to-game

  • Game Build From Design

    zenstory-ai/novel-to-game

    Builds a risk-matched whitebox or an approved production game candidate from a game design for its target runtime, with replayable evidence.

    841 GitHub stars~661 tokensUpdated 8 days ago
    Auto-check passed
  • Novel Game Adaptation Analysis

    zenstory-ai/novel-to-game

    Condenses a novel or its deconstruction notes into a cited SOURCE_BIBLE of world rules, player verbs, spaces and systems, before any game genre is chosen.

    841 GitHub stars~558 tokensUpdated 8 days ago
    Auto-check passed
  • Novel to Game

    zenstory-ai/novel-to-game

    Orchestrates turning a novel in any language into a playable game, from requirements intake and source-grounded analysis through design, build and QA.

    841 GitHub stars~567 tokensUpdated 8 days ago
    Auto-check passed
  • Game Art Direction

    zenstory-ai/novel-to-game

    Turns a game design document into an art direction document covering visual identity, HUD and feedback, sound direction and the key in-game moments.

    841 GitHub stars~384 tokensUpdated 8 days ago
    Auto-check passed
  • Evidence-Based Game QA

    zenstory-ai/novel-to-game

    Verifies a game build on its target runtime with real run evidence for launch, rendering, input, core loop, outcome and restart, and records limitations honestly.

    841 GitHub stars~389 tokensUpdated 8 days ago
    Auto-check passed
  • Game World Design

    zenstory-ai/novel-to-game

    Turns a chosen game concept into one GAME_DESIGN document covering the core loop, world rules, level beats, feedback, failure and a playable-slice contract.

    841 GitHub stars~495 tokensUpdated 8 days ago
    Auto-check passed

Questions about Novel-to-Game Concept Design

What does Novel-to-Game Concept Design do?

Compares game concepts for adapting a novel, rules out weak ones with hard vetoes and writes the chosen playable direction to a CONCEPT.md file. The skill decides what kind of game a novel should become. It writes no code, balance tables or level scripts.

When should I use Novel-to-Game Concept Design?

Novel-to-Game Concept Design fits situations like: deciding what game a novel could become; comparing candidate game directions for a book adaptation; judging whether a novel suits an interactive story.

How do I install Novel-to-Game Concept Design in Claude Code?

Run `npx skills add zenstory-ai/novel-to-game --skill game-concept -a claude-code`. Or copy the skill folder (skills/game-concept in zenstory-ai/novel-to-game) into .claude/skills/game-concept in your project. Claude Code loads it when a task matches its description.

How do I install Novel-to-Game Concept Design in Codex?

Run `npx skills add zenstory-ai/novel-to-game --skill game-concept -a codex`. Or copy the skill folder (skills/game-concept in zenstory-ai/novel-to-game) into .agents/skills/game-concept in your project. Codex loads it when a task matches its description.

Can I use Novel-to-Game Concept Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zenstory-ai/novel-to-game --skill game-concept -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/game-concept, .gemini/skills/game-concept, .github/skills/game-concept and .opencode/skills/game-concept in your project.

What does Novel-to-Game Concept Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Novel-to-Game Concept Design is instructions for the agent only. Our summary lists: SOURCE_BIBLE.md and PRODUCT_BRIEF.md in the project.

Does Novel-to-Game Concept Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel-to-Game Concept Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Novel-to-Game Concept Design use?

Novel-to-Game Concept Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel-to-Game Concept Design use?

About 423 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 735 tokens, read only when the agent opens those files.

What are the alternatives to Novel-to-Game Concept Design?

Skills that share tags, products or a category with Novel-to-Game Concept Design: Interactive Film Authoring (Narcooo/inkos, 10k stars), InkOS Interactive World Play (Narcooo/inkos, 10k stars), Game Design (ericrisco/rsc-harness, 180 stars) and Game Design Book Translator (DY-2026/GameDesignOS, 415 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel-to-Game Concept Design?

zenstory-ai (a GitHub organization) maintains it in zenstory-ai/novel-to-game, which has 841 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 3, 2026.

Source: zenstory-ai/novel-to-game on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.