zenstory-ai/novel-to-game

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 game, QA a game build, check whether the game is fully playable, or verify the build. 游戏证据化质量验证。在选定的目标运行环境中启动实?

First seen Jul 18, 2026

Installation

$ npx skills add zenstory-ai/novel-to-game --skill game-qa

Summary

  • 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 game, QA a game build, check whether the game is fully playable, or verify the build. 游戏证据化质量验证。在选定的目标运行环境中启动实??

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from zenstory-ai/novel-to-game.

npx skills add zenstory-ai/novel-to-game

Browse all from zenstory-ai/novel-to-game

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 769
License LICENSE
Default branch main
Open issues 1
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,896 B
  • docs SUMMARY.md 2,844 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 225 installs

SKILL.md

游戏质量验证

验证当前候选能否完成最小可玩闭环,不把自动化结果包装成趣味、平衡、权利或发布质量结论。

读取 [qa-contract.md](references/qa-contract.md) 定判据,按 [test-design-method.md](references/test-design-method.md) 设计最少但有区分力的检查。

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。

唯一必需合同

每个候选都必须用真实运行证据覆盖:launchrenderinputcoreLoopoutcomerestarttargetFinish 描述成色,不改变这组六项,也不得生成第七道门。

执行

  1. 读取 targetRuntimetestedRuntime 和权威 verify;与 PRODUCTBRIEF/BUILDBRIEF 冲突时先报错,

不由 QA 猜值。

  1. 运行权威 verify:它在 testedRuntime 从 clean start → 核心动作 → 设计结果 → restart

完成整条路径,并记录 command、exit code、环境、六项结果、最小证据和实际失败。

  1. 对照 GAME_DESIGN 中会改变结果的不变量和结束标记;只验证批准的设计承诺,不遍历所有

代码路径。

  1. 若候选有可执行模型、事件日志、patch 或 signature_command,按 test-design-method 的对应合同把

项目回归嵌入权威 verify;允许定向诊断、修复和复跑,最终六项证据必须来自同一次完整运行。 失败映射到已有 checks 或 limitation,不新增通用门禁,不拼接不同运行的 PASS。

  1. 记录 limitation 和问题的 product/design/art/build 归属。趣味、长期平衡、留存和商业价值只能写成

未验证风险,不给确定性 PASS。

优先使用已有可观察状态;只有无法判断结果时才增加最小测试钩子。不要为了 QA 重构游戏或强制某种 框架、测试库或调试接口。

输出

  • qa/verification.json:唯一 QA 事实源,包含三态 status、权威命令、complete run、六项 checks、

一条证据路径和 limitations;字段与证据要求见 qa-contract.md。

缺口写结构化 limitation,不发明 PASSWITHGAPS;未运行或失败的必需项不能满足整体 PASS。