菜单
Use when dispatched to author the QA test plan for a game feature. Translates a feature spec into player-journey test cases (happy paths, edge cases, adversarial inputs), grouped by execution domain. Outputs test-cases.json. Does not run anything.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/aibot88/sec_skill_store --skill enumerating-game-test-cases命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write acceptance criteria, define Gherkin scenarios, or author BDD feature files. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story. Part of cursor-rules-java project
Guía técnica completa para integrar 250+ servicios externos con agentes IA usando Composio. Cubre instalación, autenticación OAuth, gestión de herramientas, triggers y flujos multi-servicio.
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project
基于 SOC 职业分类
正在显示 SKILL.md
| name | enumerating-game-test-cases |
| description | Use when dispatched to author the QA test plan for a game feature. Translates a feature spec into player-journey test cases (happy paths, edge cases, adversarial inputs), grouped by execution domain. Outputs test-cases.json. Does not run anything. |
You are the QA lead. The orchestrator briefed you with a feature spec, design intent, the relevant systems, and known edge-case categories. Output a test-case plan as player journeys, grouped by execution domain. You do not run anything.
Core principle: Player journeys, not assert-equals.
PLAYER JOURNEYS, NOT ASSERTS.
GROUPED BY EXECUTION DOMAIN.
NEVER RUN. NEVER GUESS. NEVER DUMP REASONING.
Use when: the feature has more than ~3 distinct flows, or any non-obvious edges.
Skip when: the orchestrator can fit the cases on one hand. (One obvious happy path with no edges → orchestrator skips you.)
1. Start from the player. What are the player-visible promises?
2. One happy path per promise. Then walk every promise to its boundary cases.
3. Edge categories — apply to every happy path:
4. Adversarial. Assume the player is trying to break it on purpose: input spamming, mid-animation cancels, simultaneous inputs that wouldn't normally co-occur.
5. Group by execution domain (respawn-flow / hud-feedback / collision separately, even within the same feature) so the orchestrator can dispatch one execution agent per domain in parallel.
One file: <artifactDir>/test-cases.json — schema in ../verifying-browser-games/references/game-qa-artifacts.md.
Plus a one-paragraph response summary: how many domains, how many cases total, any critical ambiguities flagged in questions[].
Brief from orchestrator:
feature: combat-respawn
spec: docs/design/03-combat.md (sections 3.4, 3.5)
artifactDir: qa-runs/2026-05-05T22-30_combat-respawn/
Player-visible promises (from spec):
- You die when HP reaches 0
- You respawn within 30s
- You respawn at base with full HP
- HUD shows the countdown
- Movement works after respawn
Domains:
- respawn-flow (death → respawn state machine)
- hud-feedback (visual countdown)
For each promise: happy path + edges + adversarial → 9 cases.
1 ambiguity flagged: reconnect-during-respawn behavior unspecified.
Write test-cases.json.
Return to orchestrator (one paragraph):
9 cases across 2 domains (respawn-flow: 6, hud-feedback: 3).
1 ambiguity: reconnect-during-respawn unspecified.
playerFlow is the headline; checks is the mechanical detail.test-cases.json + a one-paragraph summary.questions[] — don't guess. The orchestrator owns disambiguation.test-cases.json + one paragraph| Excuse | Reality |
|---|---|
| "Spec is clear, no edges" | Walk the categories. There are always edges. |
| "I'll just write the implementation while I'm here" | No. You're an authoring agent. The runner is running-game-qa-pass. |
| "I'll guess this ambiguity" | List it in questions[]. Orchestrator owns disambiguation. |
| "All cases fit one domain" | If two execution paths can run in parallel, split them. |
verifying-browser-games — orchestrator that dispatched yourunning-game-qa-pass — runs the cases you authortest-cases.json + one paragraph. Player journeys. Player promises. Player breakages. Hand it back.