Game Boy ROM Playthrough Driver
trekawek/coffee-gb
Plays an authorized Game Boy or Game Boy Color ROM in one persistent headless Coffee GB session, inspecting frames and keeping an action trace for replay or tests.
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.
SKILL.md written in Chinese; this summary is our English description.
Install Evidence-Based Game QA
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zenstory-ai/novel-to-game game-qa --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-qa .claude/skills/game-qa && rm -rf skills-srcUse ~/.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/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .claude/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zenstory-ai/novel-to-game game-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/game-qa .agents/skills/game-qa && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .agents/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zenstory-ai/novel-to-game game-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/game-qa .cursor/skills/game-qa && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .cursor/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zenstory-ai/novel-to-game.git --path skills/game-qa--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zenstory-ai/novel-to-game game-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/game-qa .gemini/skills/game-qa && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .gemini/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zenstory-ai/novel-to-game game-qaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/game-qa .github/skills/game-qa && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .github/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/novel-to-game --skill game-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zenstory-ai/novel-to-game game-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/novel-to-game.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/game-qa .opencode/skills/game-qa && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "game-qa" agent skill from https://github.com/zenstory-ai/novel-to-game/tree/main/skills/game-qa into .opencode/skills/game-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-qa", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
game-qa- GitHub stars
- 841
- Token cost
- ~389 tokens
- SKILL.md length
- 74 words
- Files
- 4 (incl. references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
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.
- Works in 5 steps: 读取 targetRuntime、testedRuntime 和权威… → 运行权威 verify：它在 testedRuntime 从 clean… → 对照 GAME_DESIGN… → …
- Testing a generated game build before calling it playable
- SKILL.md covers 唯一必需合同, 执行 and 输出
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill is written in Chinese and checks whether a candidate game can complete a minimal playable loop. It does not present automated results as a verdict on fun, balance, rights or release quality. Every candidate must be covered by real runtime evidence for six items: launch, render, input, coreLoop, outcome and restart, and a finish-quality field describes polish without adding a seventh gate.
The agent reads the target and tested runtimes and the authoritative verify command, stops with an error if they conflict with the product or build briefs, and runs the verify from a clean start through the core action, a designed outcome and restart. It records the command, exit code, environment, the six results, minimal evidence and actual failures, and checks only the invariants and end markers promised in the game design.
Results go into qa/verification.json, the single source of truth, with gaps written as structured limitations attributed to product, design, art or build. No PASS_WITH_GAPS status is invented, and an unrun or failed required item blocks an overall pass. Existing observable state is preferred, and minimal test hooks are added only when needed. Two references define the QA contract and the test design method.
When your agent uses it
- Testing a generated game build before calling it playable
- Checking that a game launches, renders, accepts input and can restart
- Recording honest limitations for a game candidate
Example prompts
- “QA the browser game in ./build and write qa/verification.json with evidence for all six checks.”
- “Check whether this game is fully playable from launch to a designed outcome and restart.”
- “Verify the latest build and list its limitations by product, design, art and build.”
Requirements
- A runnable game build and its authoritative verify command
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 读取 targetRuntime、testedRuntime 和权威 verify；与 PRODUCT_BRIEF/BUILD_BRIEF 冲突时先报错，
- 运行权威 verify：它在 testedRuntime 从 clean start → 核心动作 → 设计结果 → restart
- 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
- 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
- 记录 limitation 和问题的 product/design/art/build 归属。
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
Evidence-Based Game QA loads about 389 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 74 words of instructions outside code blocks.
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). 74 words, ~389 tokens.
Download SKILL.mdSave it as
.claude/skills/game-qa/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- game-qa
- description
- 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际构建，证明真实渲染、输入、核心循环、至少一个设计结果、重开和明确限制，不把主观趣味包装成确定性结论。用于测试生成游戏、检查游戏能否完整游玩或验证构建。
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 定判据，按 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：launch、render、input、coreLoop、outcome、restart。
targetFinish 描述成色，不改变这组六项，也不得生成第七道门。
执行
- 读取
targetRuntime、testedRuntime和权威 verify；与 PRODUCT_BRIEF/BUILD_BRIEF 冲突时先报错， 不由 QA 猜值。 - 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。
- 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。
- 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。 - 记录 limitation 和问题的 product/design/art/build 归属。
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；字段与证据要求见 qa-contract.md。
缺口写结构化 limitation，不发明 PASS_WITH_GAPS；未运行或失败的必需项不能满足整体 PASS。
© 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 3 other files (references) in skills/game-qa of zenstory-ai/novel-to-game.
- SKILL.md
- agents/openai.yaml
- references/qa-contract.md
- references/test-design-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
Evidence-Based Game QA 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Evidence-Based Game QA this skillzenstory-ai/novel-to-game | 841 | — | ~389 | Automated safety check: Pass | MIT | |
| Game Boy ROM Playthrough Drivertrekawek/coffee-gb | 1.2k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Build Game Inventorynirholas/three.ws | 229 | 1 repos | ~418 | Automated safety check: Pass | Apache-2.0 | |
| Ship Web Gamesnirholas/three.ws | 229 | 1 repos | ~284 | Automated safety check: Pass | Apache-2.0 | |
| Tiny Game Controllerminigdx/tiny | 164 | — | ~874 | Automated safety check: Pass | MIT | |
| Test Playable Web Gamesnirholas/three.ws | 229 | 1 repos | ~429 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Build Game Inventory
nirholas/three.ws
Build or repair game inventory, loot, equipment, tooltips, drag-and-drop, persistence, and progression systems.
Ship Web Games
nirholas/three.ws
Package, deploy, and verify a playable Three.js or web game.
Tiny Game Controller
minigdx/tiny
Controls a running Tiny game engine over its local debug HTTP server, sending key presses, releases and taps so the agent can play or test the game.
Test Playable Web Games
nirholas/three.ws
Test a playable browser game end to end with deterministic fixtures and real browser evidence.
KenshiCoop Save Orchestration
nhoral/KenshiCoop
Picks the right save file and script for a KenshiCoop debugging or validation session, and protects version-controlled fixtures from being overwritten.
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.
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.
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.
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.
Novel-to-Game Concept Design
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.
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.
Related
Categories
Questions about Evidence-Based Game QA
What does Evidence-Based Game QA do?
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. The skill is written in Chinese and checks whether a candidate game can complete a minimal playable loop. It does not present automated results as a verdict on fun, balance, rights or release quality.
When should I use Evidence-Based Game QA?
Evidence-Based Game QA fits situations like: testing a generated game build before calling it playable; checking that a game launches, renders, accepts input and can restart; recording honest limitations for a game candidate.
How do I install Evidence-Based Game QA in Claude Code?
Run `npx skills add zenstory-ai/novel-to-game --skill game-qa -a claude-code`. Or copy the skill folder (skills/game-qa in zenstory-ai/novel-to-game) into .claude/skills/game-qa in your project. Claude Code loads it when a task matches its description.
How do I install Evidence-Based Game QA in Codex?
Run `npx skills add zenstory-ai/novel-to-game --skill game-qa -a codex`. Or copy the skill folder (skills/game-qa in zenstory-ai/novel-to-game) into .agents/skills/game-qa in your project. Codex loads it when a task matches its description.
Can I use Evidence-Based Game QA 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-qa -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-qa, .gemini/skills/game-qa, .github/skills/game-qa and .opencode/skills/game-qa in your project.
What does Evidence-Based Game QA need to run?
SKILL.md names no scripts, command-line tools or credentials: Evidence-Based Game QA is instructions for the agent only. Our summary lists: A runnable game build and its authoritative verify command.
Does Evidence-Based Game QA 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 Evidence-Based Game QA 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 Evidence-Based Game QA use?
Evidence-Based Game QA 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 Evidence-Based Game QA use?
About 389 tokens (SKILL.md is roughly 1.6k 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 1.7k tokens, read only when the agent opens those files.
What are the alternatives to Evidence-Based Game QA?
Skills that share tags, products or a category with Evidence-Based Game QA: Game Boy ROM Playthrough Driver (trekawek/coffee-gb, 1.2k stars), Build Game Inventory (nirholas/three.ws, 229 stars), Ship Web Games (nirholas/three.ws, 229 stars) and Tiny Game Controller (minigdx/tiny, 164 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evidence-Based Game QA?
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.