zenstory-ai/novel-to-game / skills/game-qa
game-qa
VerifiedBlind-playtest and verify a game on its target runtime as a first-time player without reading source code. Runs an isolated cold-start playthrough to catch onboarding, interaction, pacing, and mobile viewport issues, checks findings against the design specs, and writes a complete-run verification record. Use to blind-playtest a game build as a new player, audit first-run playability, or run end-to-end game QA. 游戏盲玩与通关验收:先以未读源码和策划案的新玩家身份从头盲玩,排查上手引导、交互卡点、视听穿帮与手机视口问题,再对照策划案区分缺陷与设计边界,并实跑生成单次完整通关的验收记录。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.9 KB |
| agents/openai.yaml | config | 314 B |
| references/blind-playtest-method.md | markdown | 4.1 KB |
| references/qa-contract.md | markdown | 3.0 KB |
SKILL.md
View on GitHub---
name: game-qa
description: "Blind-playtest and verify a game on its target runtime as a first-time player without reading source code. Runs an isolated cold-start playthrough to catch onboarding, interaction, pacing, and mobile viewport issues, checks findings against the design specs, and writes a complete-run verification record. Use to blind-playtest a game build as a new player, audit first-run playability, or run end-to-end game QA. 游戏盲玩与通关验收:先以未读源码和策划案的新玩家身份从头盲玩,排查上手引导、交互卡点、视听穿帮与手机视口问题,再对照策划案区分缺陷与设计边界,并实跑生成单次完整通关的验收记录。"
---
# 游戏盲玩与通关验收
以第一次点开游戏的新玩家视角完成盲玩与通关验收。不读源码,不替构建阶段补写测试,也不把跑通流程说成好玩、数值平衡、版权合规或已达上线水准。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。
## 流程
在与编码隔离的独立会话中执行。无论哪种 `targetFinish`,都必须跑完从头盲玩与 `launch`、`render`、`input`、`coreLoop`、`outcome`、`restart` 六项检查;`graybox` 仅免检最终美术与配音成色。
1. **冷启动隔离**:首轮盲玩结束前,严禁读取游戏源码、剧本数据、测试脚本、内部状态,也严禁读取 `SOURCE_BIBLE.md`、`CONCEPT.md`、`GAME_DESIGN.md`、`ART_DIRECTION.md`、`_progress.md`、过往的 `qa/playtest-report.md` 及提交记录。只从 `BUILD_BRIEF.md` 的 `# 运行` 一节读取启动命令与运行环境,从 `PRODUCT_BRIEF.md` 读取视口与分级要求;两处矛盾时直接报错退回。
2. **第一轮 · 新玩家盲玩**:在全新浏览器或窗口会话中从标题页启动,全靠屏幕画面、声音与正常操作打通至少一个设计结局,并实测刷新后的存档恢复、重开回初态及手机窄屏下的关键路径。不注入存档,不调内部接口,也不偷看隐藏 DOM 或内存变量。
3. **第二轮 · 对照核实与端到端验证**:盲玩跑完后才读取全套设计文档与完整 `BUILD_BRIEF.md`,把首轮遇到的卡点拆清为「实现或引导缺陷」与「设计有意的边界」;随后在 `testedRuntime` 执行 `BUILD_BRIEF.md` 声明的端到端 `verify` 命令。
4. **交付**:输出盲玩诊断报告 `qa/playtest-report.md` 与机器可读验收记录 `qa/verification.json`,未实测的范围如实写入 `limitations`。只要盲玩证实存在 `P0` 阻断,哪怕自动化脚本绕开界面跑通,对应检查项与顶层 `status` 也一律记 `FAIL`。`P0`、`P1` 及核心体验硬伤按 `product` / `design` / `art` / `build` 归属退回,从源头修复。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |