Skip to content

/game-qa

Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated

From plugin
novel-to-game
9537 skills

Claude Code

$ npx -y skills add zenstory-ai/novel-to-game --skill game-qa --agent claude-code

SKILL.md

game-qa.SKILL.md
name: game-qa
description: "Blind-playtest and verify a game on its target runtime as a first-time player without reading source code. Run an isolated zero-knowledge playthrough first to uncover onboarding, guidance, interaction, pacing, and mobile viewport issues, then reconcile against design specs and record one complete-run verification receipt. Use for blind playtest a generated game, QA a game build as a new player, audit first-run playability, or verify a game build. 游戏实机盲玩与运行验收。先以未读源码与设计文档的新玩家身份在目标运行环境中从头盲玩,排查上手引导、交互动线、视听节奏与视口适配问题,再对照设计规范核实定性,并用单次完整通关记录生成验收凭证。用于新玩家视角盲测游戏、诊断实机体验问题或验收构建版本。"

游戏实机盲玩与运行验收

站在第一次打开游戏的真实玩家视角完成实机盲玩与通关验收,不做源码走读、不审查内部函数、也不替构建阶段补写单元测试,更不把跑通测试包装成“好玩、数值平衡、版权合规或达到商业上线水准”的定论。开始前先读 [blind-playtest-method.md](references/blind-playtest-method.md) 与 [qa-contract.md](references/qa-contract.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。

两轮验收流程

优先在未参与编码的独立会话中执行。任何构建版本都必须跑通 `launch`、`render`、`input`、`coreLoop`、`outcome`、`restart` 六项实机检查与首轮冷启动盲玩(`targetFinish` 只代表视觉与制作完成度,不增减六项基础检查;`graybox` 同样执行冷启动盲玩,只免检最终美术与配音成色):

1. **首轮隔离与开跑准备**:**首轮盲玩结束前,严禁读取游戏源码、剧本数据、测试脚本、`SOURCE_BIBLE.md`、`CONCEPT.md`、`GAME_DESIGN.md`、`ART_DIRECTION.md`、`BUILD_BRIEF.md` 的 `# 必须保真 / # 最小实现与复现` 小节或内部状态快照**;只提取 `BUILD_BRIEF.md` `# 运行` 小节的启动命令、`targetRuntime`、`testedRuntime` 以及 `PRODUCT_BRIEF.md` 的视口与分级边界(两者前后矛盾时立即报错退回)。在仓库外建立独立的运行记录目录,每条命令显式传入字面路径与独立会话标识,避免跨命令丢失环境变量或串用浏览器存档。 2. **第一轮 · 新玩家实机盲玩**:按 [blind-playtest-method.md](references/blind-playtest-method.md) 从标题页纯净启动(绝不注入测试存档、调用内部跳过接口或偷看隐藏 DOM/内存变量),仅凭屏幕可见画面、声音表现与正常输入推进到至少一个设计结局,并实测刷新/重进后的存档恢复、重开回初态以及手机窄屏(如 `390×844`)关键路径。随步骤同步截取画面、收集控制台与请求报错,并用玩家口吻实时写下带时间戳的**出声思考日志**(含首屏五秒理解、每阶段 `0–4` 摩擦分、惊喜时刻与流失时刻)。 3. **第二轮 · 规范核对与权威验证**:首轮盲玩完整结束后,才读取 `GAME_DESIGN.md`、`ART_DIRECTION.md`、`PRODUCT_BRIEF.md` 与完整 `BUILD_BRIEF.md` 核对首轮记录的困惑,分清“功能缺陷或引导缺失”与“设计有意如此的规则边界”;随后在 `testedRuntime` 中运行 `BUILD_BRIEF.md` 声明的权威 `verify` 命令,核验从纯净初态到设计结局再重开的单次完整运行闭环。 4. **交付诊断报告与验收记录**:

  • 按 [blind-playtest-method.md](references/blind-playtest-method.md) 产出盲玩诊断报告 `qa/playtest-report.md`(过程连拍与原始日志留在仓库外运行目录,工作区 `qa/` 只存精简报告与证明问题的关键截图,严禁出现密码、令牌或 Cookie)。
  • 按 [qa-contract.md](references/qa-contract.md) 生成唯一的机器验收凭证 `qa/verification.json`,未覆盖范围如实记入 `limitations`。**若首轮盲玩证实存在 `P0` 阻断(如必经按钮被遮挡无法点击、主线死胡同、崩溃白屏),即便自动化脚本绕过界面跑通,对应 `checks` 项与顶层 `status` 均须标为 `FAIL`**;暴露的 `P0`/`P1` 及核心体验问题按 `product` / `design` / `art` / `build` 职责归属退回对应环节从根源修复。
Read more
@zenstory-ai
Ships withnovel-to-game

Agent skills for source-grounded novel-to-game adaptation (小说改编游戏 / story to game): cited design docs, target-runtime builds, evidence-based QA. Three playable browser examples. For Claude Code, Codex, and Kimi Code.

Stars on GitHub

Momentum

stars in total
953
Star history of zenstory-ai/novel-to-game on GitHub, a chart by star-history.com

Other skills on novel-to-game.

game-build
Auto-invoked

game-build

Build a risk-matched whitebox or the approved production game for its target runtime. Turn GAME_DESIGN, and ART_DIRECTION when…

game-concept
Auto-invoked

game-concept

Design game concepts from a novel. From SOURCE_BIBLE and PRODUCT_BRIEF, compare meaningful alternatives on the dimensions still…

game-world-design
Auto-invoked

game-world-design

Design game experience, systems, and levels. Converge the chosen concept into one GAME_DESIGN defining the player promise, core…

novel-game-analyze
Auto-invoked

novel-game-analyze

Deconstruct a novel for game adaptation. Compress a raw novel, deconstruction library, or writing project into a SOURCE_BIBLE…

novel-to-game
Auto-invoked

novel-to-game

Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline —…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react3d252k
@facebook@facebookInstall Skill

Questions about game-qa.

Which coding agents can use game-qa?
game-qa installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.