Threejs Gameplay Systems
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。
Install Game Concept Architect
$ npx skills add DY-2026/GameDesignOS --skill game-concept-architect -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DY-2026/GameDesignOS game-concept-architect --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/DY-2026/GameDesignOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/game-concept-architect .claude/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .claude/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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/DY-2026/GameDesignOS/tree/main/game-concept-architectType 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 DY-2026/GameDesignOS --skill game-concept-architect -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DY-2026/GameDesignOS game-concept-architect --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/game-concept-architect .agents/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .agents/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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 DY-2026/GameDesignOS --skill game-concept-architect -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DY-2026/GameDesignOS game-concept-architect --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/game-concept-architect .cursor/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .cursor/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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/DY-2026/GameDesignOS.git --path game-concept-architect--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 DY-2026/GameDesignOS --skill game-concept-architect -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DY-2026/GameDesignOS game-concept-architect --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/game-concept-architect .gemini/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .gemini/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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 DY-2026/GameDesignOS game-concept-architectInstalls 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 DY-2026/GameDesignOS --skill game-concept-architect -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/game-concept-architect .github/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .github/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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 DY-2026/GameDesignOS --skill game-concept-architect -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DY-2026/GameDesignOS game-concept-architect --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/game-concept-architect .opencode/skills/game-concept-architect && 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-concept-architect" agent skill from https://github.com/DY-2026/GameDesignOS/tree/main/game-concept-architect into .opencode/skills/game-concept-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-concept-architect", 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-concept-architect- GitHub stars
- 415
- Token cost
- ~2.1k tokens
- SKILL.md length
- 464 words
- Files
- 52 (incl. references, assets)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。
- Works in 9 steps: concept seed extraction → player verb inventory → design nucleus options → …
- Tasks that involve Game design
- SKILL.md covers 强制顺序, 默认工作流, External Evidence Status / VOI… and Case Visibility, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Game Concept Architect is an agent skill from DY-2026/GameDesignOS. 将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 56 other files, including reference files and assets (for example `README.md`, `agents/openai.yaml` and `evals/behavior_evals.json`). Compatibility notes: 需要读取用户提供的项目资料；联网调研与写入项目文件仅在任务明确需要时使用。
It sits in Game Development, covering Game design. The repository describes itself as: Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback. The licence is MIT.
When your agent uses it
- Tasks that involve Game design
Example prompts
- “/game-concept-architect”
Requirements
- Compatibility (from SKILL.md): 需要读取用户提供的项目资料；联网调研与写入项目文件仅在任务明确需要时使用。
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- concept seed extraction
- player verb inventory
- design nucleus options
- action-goal alignment
- assumption ledger
- player promise
- core loop
- scope gate
- validation plan
What it can do on your machine
Read from SKILL.md and the folder at commit ada4bf9. 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 (its code samples are markdown).
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.
Compatibility
需要读取用户提供的项目资料；联网调研与写入项目文件仅在任务明确需要时使用。
From compatibility in the SKILL.md frontmatter.
Context cost
Game Concept Architect loads about 2.1k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 464 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 DY-2026/GameDesignOS at commit ada4bf9, republished under its MIT licence (© DY-2026). 464 words, ~2,111 tokens.
Download SKILL.mdSave it as
.claude/skills/game-concept-architect/SKILL.md (or your agent's skills folder). This skill also uses 51 other files; get the full folder from GitHub.- name
- game-concept-architect
- description
- 将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。
- compatibility
- 需要读取用户提供的项目资料；联网调研与写入项目文件仅在任务明确需要时使用。
- license
- MIT
- metadata.version
- 1.3.0-candidate
- metadata.short-description
- 将游戏创意编译为可验证的设计蓝图
Game Concept Architect
使用本 skill 时，把一句话游戏创意转化为可以判断、可以裁剪、可以原型验证的游戏设计蓝图。
不要把自己当成普通 GDD 生成器。不要在提取 design seed、比较 design nucleus options 和标注 assumptions 之前，直接扩写世界观、功能列表或看似确定的生产计划。
用户可在自己的环境中处理真实项目、私有项目或客户项目。准备公开仓库案例时，只能使用 synthetic、公开或明确授权的材料，并在发布前执行 Human Gate。
强制顺序
在输出任何设计案之前，必须按下面顺序完成。用户要求简短时可以压缩，但不要跳过 gate。
concept seed extractionplayer verb inventorydesign nucleus optionsaction-goal alignmentassumption ledgerplayer promisecore loopscope gatevalidation plan
当输入涉及参考游戏、机制迁移、完整方案、玩法审查、受众动机、随机性、长期内容或主题表达时，启用 game dissection lens。只展开会改变关键设计判断的层级，不要为了显得完整而把所有模板都塞进输出。
默认工作流
- 记录 case visibility，只用于输出管理，不用于限制用户在自己环境中分析真实项目：
case_visibility:private_user_work|public_repo_example|public_article|client_confidential|synthetic_case|unknownoutput_destination:private_notes|repo_example|public_post|client_delivery|unknownredaction_required:true|false|unknown
- 用一句话复述用户原始创意。
- 提取 concept seed：
- 题材母体
- 玩法母体
- 情绪承诺
- 差异化种子
- 平台假设
- 商业化假设
- 受众假设
- 关键 unknown
- 做 player verb inventory：
- 玩家直接动作
- 系统响应或间接动作
- 玩家脑内判断、预测、权衡
- 界面动作是否服务核心循环
- 80% 时间里玩家真正反复做什么
- 生成 2 到 4 个 design nucleus options。每个候选都要写清：
- 玩家反复做什么取舍
- 它改变什么行为、节奏、成长或表达
- 它依赖哪些 assumptions
- 它最适合的受众、平台和生产画像
- 它的最大风险和最小验证方式
- 做 action-goal alignment：
- 核心动词是否推进瞬时目标、局内目标和长期目标
- 简单动作是否被多层目标放大
- 是否存在脱离核心循环的目标或功能
- 玩家自发目标是否可被系统支持，而不是被强制
- 做 external evidence status / VOI feasibility gate：
- 不强制联网，不做泛搜。
- 只有当外部信息会改变 design nucleus、target audience、platform fit、business model、scope gate、validation plan 或 Go/No-Go 时，才做外部调研。
- 没有当前证据时，标记
not-run或evidence-needed，不得写成确定市场判断。
- 将所有用户未提供的信息标记为 assumption 或 unknown，并说明置信度、影响等级和验证方式。
- 选择或建议一个 design nucleus 后，先定义玩家承诺：
- 对外宣传承诺
- 前 10 分钟承诺
- 长期游玩承诺
- 构建核心循环：
- 行动
- 选择
- 风险
- 反馈
- 奖励
- 成长或新约束
- 做 uncertainty calibration：
- 不确定性来自人、隐藏信息、身体技能、脑力技能还是随机性
- 它降低分析瘫痪、制造变化、形成追赶，还是掩盖设计问题
- 玩家是否能解释失败原因
- 随机性是否覆盖了玩家努力
- 只有当新增系统能说清以下内容时，才允许加入：
- 它服务哪个核心循环
- 它改变什么玩家行为
- 它创造什么反馈
- 它如何被验证
- 对关键系统做 dynamics / content / audience / theme 检查：
- 规则组合后会产生什么玩家动态和阶段
- 内容是否来自核心循环变奏，而不是靠堆量续命
- 受众假设是否写成行为、动机和拒绝点，而不是标签
- 主题是否被操作、选择和后果承载
- 做 production feasibility check：
- 团队能力未知时，不要默认开放世界、实时多人、长期 live ops、大量剧情分支或高精度物理可做。
- 技术方案是否有成熟参考、可替代方案或可验证原型。
- 内容和高光时刻是否能持续产出。
- 时间、预算、外包、工具链和商业预期是否匹配。
- 执行 scope gate：
- MVP 必须有
- Vertical Slice 应该有
- Demo 后再做
- 宣传概念可以保留但暂不开发
- 建议砍掉的危险设计
- 输出 validation plan：
- 最小可玩原型
- 第一轮测试目标
- 最危险假设
- 通过标准
- 失败标准
- 下一步投入条件
- 根据用户需求选择输出模式并组织最终交付。
External Evidence Status / VOI Feasibility Gate
外部证据不是固定步骤，而是 VOI 决策。只有当调研结果可能改变关键设计选择时才值得做。
| 状态 | 含义 | 输出要求 |
|---|---|---|
not-run | 当前没有做外部调研，且 VOI 不足或用户未要求 | 写明不运行原因和后续触发条件 |
evidence-needed | 关键判断需要证据，但当前没有来源 | 不得写成市场事实，列出最小验证动作 |
partial | 有间接证据，但不足以支撑 Go/No-Go | 标出哪些设计判断仍是假设 |
verified | 有当前来源、链接、数据、评论或公开材料支持 | 说明证据改变了哪个 gate |
contradicted | 外部证据冲突或削弱原假设 | 调整 nucleus、scope 或验证计划 |
外部调研的 VOI 问题：
- 会不会改变 design nucleus 的选择？
- 会不会改变 target audience、platform fit 或 business model？
- 会不会改变 MVP / Vertical Slice 范围？
- 会不会改变第一轮原型验证指标？
- 会不会改变 Go/No-Go、pivot 或暂停判断？
Show full SKILL.md (171 more words)Show less
Case Visibility
case_visibility 只帮助 agent 管理输出边界，不限制用户在本地环境中处理真实、私有或客户项目。
当 output_destination=repo_example 时，仓库 examples、assets、showcases、eval cases 只能使用 synthetic cases、公开材料或明确 cleared materials，并在发布前执行 Human Gate。
当 output_destination=private_notes 或 client_delivery 时，按用户目标完成分析；不要把本公开仓库的贡献规则误当成用户私有工作限制。
输出模式
| 模式 | 默认触发 | 交付重点 |
|---|---|---|
idea_triage | 用户只给一句话，且没有指定完整方案 | 快速拆 seed、列 design nucleus options、标 unknown、必要时补 player verbs 和 action-goal 风险 |
one_page_pitch | 用户要 pitch、轻量方案或立项判断 | 一页 pitch、玩家承诺、核心循环、scope 摘要、验证计划摘要 |
full_design_brief | 用户要完整方案、完整设计案、制作前文档 | seed、verbs、nucleus、assumptions、承诺、循环、系统、平台商业、生产可行性、scope、风险、验证 |
vertical_slice_plan | 用户要原型制作、demo、first playable、里程碑计划 | 垂直切片目标、功能优先级、生产边界、里程碑、测试标准、下一步投入条件 |
如果用户只给一句话且没有指定完整方案，默认使用 idea_triage。如果用户明确要求完整方案，使用 full_design_brief；如果用户要求原型或 demo 计划，使用 vertical_slice_plan。
资源加载指南
按任务需要加载对应 reference，不要一次性塞入所有资料：
- 在扩展任何一句话创意前，优先使用
references/concept-seed-extraction.zh-CN.md。 - 当输入涉及参考游戏、机制迁移、完整玩法方案、受众动机、随机性、内容流或主题表达时，使用
references/game-dissection-lens.zh-CN.md。 - 在比较设计核候选时，使用
references/design-nucleus-options.zh-CN.md。 - 在判断是否需要外部调研时，使用
references/voi-feasibility-gate.zh-CN.md。 - 在书写玩家承诺前，使用
references/player-promise-framework.zh-CN.md。 - 当需要把承诺转成循环和系统时，使用
references/core-loop-expansion.zh-CN.md。 - 当创意涉及品类、融合品类或参考游戏时，使用
references/genre-fit-matrix.zh-CN.md和references/reference-game-boundary.zh-CN.md。 - 在承诺功能范围前，使用
references/scope-gate.zh-CN.md。 - 在判断是否值得继续投入前，使用
references/prototype-validation-gate.zh-CN.md。 - 当平台、商业化、广告、IAP、买断、live ops、移动端、PC、Web、主机或小游戏约束会影响设计时，使用
references/platform-business-fit.zh-CN.md。 - 当需要评估团队能力、技术成熟度、内容产能、成本和周期时，使用
references/production-feasibility.zh-CN.md和references/production-profile-gate.zh-CN.md。
按最终交付选择 template：
templates/idea-triage.mdtemplates/player-verb-inventory.mdtemplates/design-nucleus-options.mdtemplates/action-goal-alignment.mdtemplates/uncertainty-calibration.mdtemplates/system-dynamics-map.mdtemplates/content-flow-plan.mdtemplates/audience-desire-map.mdtemplates/playable-theme-map.mdtemplates/player-promise-contract.mdtemplates/reference-game-boundary.mdtemplates/production-profile.mdtemplates/one-page-pitch.mdtemplates/full-design-brief.mdtemplates/vertical-slice-plan.mdtemplates/assumption-ledger.mdtemplates/risk-register.mdtemplates/validation-plan.mdtemplates/feature-priority-matrix.mdtemplates/feasibility-scan.mdtemplates/production-budget-snapshot.md
使用 examples 时只参考结构和表达方式，不要机械套用；当前 examples 均为 synthetic cases：
examples/clockwork-garden-defense.mdexamples/clockwork-garden-defense-illustrated.mdexamples/dream-postman-card-adventure.mdexamples/tiny-crew-space-salvage.md
硬规则
- 不要把题材当差异化。题材组合只有在改变玩家行为时，才可能成为设计核。
- 不要把世界观当玩法。设定必须创造行动、约束或选择，才有设计价值。
- 不要只列功能名；必须能说清玩家反复执行的动词，以及这些动词如何接到目标。
- 不要把随机性当万能调味料；必须说明它来自哪里、放在哪里、玩家如何理解失败。
- 不要用“内容很多”弥补核心循环薄弱；内容必须是核心循环的变奏和延展。
- 不要把受众写成人口标签；必须写出玩家想做什么、为什么兴奋、为什么反感。
- 不要把主题停留在剧情或美术；主题必须被操作、选择和后果承载。
- 不要因为某个系统是品类标配就加入它。
- 不要在一句话创意有多个合理方向时，过早锁死单一设计核。
- 不要把 assumption 藏在确定语气里。
- 不要输出无法测试的完整幻想文档。
- 当目标平台被说出或明显暗示时，不要跳过平台和商业适配。
- 不要把没有外部证据的市场判断写成事实。
- 不要为了显得完整而泛搜；先说明 VOI。
- 不要复制参考游戏的结构、术语、设定、阵营或内容表达；只抽取行为结构。
- 不要把团队未知或不可控的能力设计成核心卖点。
- 不要承诺需要长期大量内容产出的高光体验，除非写清内容产能验证方式。
- 没有通过标准和失败标准时，不要建议继续生产投入。
- 不要用“后续调优”代替验证计划。
- 不要把
repo_example贡献规则误用为用户私有工作限制。
最低合格输出
idea_triage 至少包含：
## Case Visibility
## Original Idea
## Concept Seed Extraction
## Player Verb Inventory
## Design Nucleus Options
## Action-Goal Alignment
## Assumption Ledger
## External Evidence Status
## Recommended Next Stepone_page_pitch、full_design_brief 和 vertical_slice_plan 至少包含：
## Case Visibility
## Concept Seed Extraction
## Player Verb Inventory
## Design Nucleus Options
## Action-Goal Alignment
## Assumption Ledger
## External Evidence Status
## Player Promise
## Core Loop
## Production Feasibility
## Scope Gate
## Validation Plan当使用 full_design_brief 时，还要包含：
## Key Systems
## Uncertainty Calibration
## System Dynamics Map
## Content Flow Plan
## Audience Desire Map
## Playable Theme Map
## Platform and Business Fit
## Reference Game Boundary
## Feature Priority Matrix
## Risk Register
## Cost and Content Feasibility当使用 vertical_slice_plan 时，还要包含：
## Vertical Slice Goal
## Build Scope
## Milestones
## Playtest Protocol
## Next Investment Decision输入不足时的处理
如果一句话创意过于模糊，不要默认停下。先输出 idea_triage 的低置信度版本，并清楚标记 assumptions。
只有当缺失信息会实质改变设计方向时，才提出澄清问题，例如目标平台、商业模式、团队规模、参考游戏是灵感来源还是硬约束。
澄清问题最多问三个。如果用户要求继续，就带着明确 assumptions 往前推进。
© DY-2026, 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 51 other files (references, assets) in game-concept-architect of DY-2026/GameDesignOS.
- SKILL.md
- README.md
- agents/openai.yaml
- assets/clockwork-garden-defense-key-art.png
- evals/behavior_evals.json
- evals/evals.json
- evals/negative_cases.md
- evals/rubric.yaml
- evals/synthetic_outputs.json
- examples/README.md
- examples/clockwork-garden-defense-illustrated.md
- examples/clockwork-garden-defense.md
- examples/dream-postman-card-adventure.md
- examples/tiny-crew-space-salvage.md
- references/concept-seed-extraction.zh-CN.md
- references/core-loop-expansion.zh-CN.md
- … and 36 more
Open the folder on GitHubat commit ada4bf9
Compare with similar skills
Game Concept Architect 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 |
|---|---|---|---|---|---|---|
| Game Concept Architect this skillDY-2026/GameDesignOS | 415 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Threejs Gameplay Systemsvalkor-ai/loom | 1.2k | 1 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Godot Gdscript Patterns925236118/AlphaAgent | 103 | 10 repos | ~5k | Automated safety check: Pass | MIT | |
| Game Asset Spec WriterDonchitos/Claude-Code-Game-Studios | 26k | — | ~5k | Automated safety check: Pass | MIT | |
| Game Build From Designzenstory-ai/novel-to-game | 841 | — | ~661 | Automated safety check: Pass | MIT | |
| Threejs Gameplay Systemscorosolto/client | 257 | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Godot Gdscript Patterns
925236118/AlphaAgent
Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.
Game Asset Spec Writer
Donchitos/Claude-Code-Game-Studios
Writes per-asset visual specs and AI image-generation prompts for a game's characters, enemies and screens, driven by the GDD, art bible and an entity inventory.
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.
Threejs Gameplay Systems
corosolto/client
Build and iterate playable Three.js game systems. An agent skill from corosolto/client.
Roblox Game
brockmartin/roblox-game-skill
Expert Roblox game development companion — Luau, Roblox Studio, MCP integration, simulator, tycoon, obby, RPG, horror, battle royale, game design, security, performance.
More from DY-2026/GameDesignOS
Game Experience Density Optimizer
DY-2026/GameDesignOS
当用户需要把游戏体验浓度、留存、首局节奏、Demo 完成率、单机总旅程、D1/D7、反馈、具身感、氛围、认知负荷、最佳刺激窗口、FEP/free-energy、预测误差、Markov blanket、习惯化或 liveops 参与问题，编译成可上线、可埋点、可复盘、可回滚的一周 ED 实验包时使用。Use when converting game experience-density and…
Paranoia AI System Evolver
DY-2026/GameDesignOS
用于升级 AI 系统、agent workflow、Codex skill、prompt、memory、RAG、tool routing、schema、eval set 或 feedback loop；也用于把 AI 工作单从指令单升级为意图单，并对研究、检索、测试和 AI 对话做 VOI 决策门审计。需要 Intent Work Order、WOOP…
Game Design Book Translator
DY-2026/GameDesignOS
用于翻译、润色、整理或质检英文游戏设计、游戏研发、系统设计、UX、Game Studies 与设计理论书籍、章节、PDF、OCR、Markdown、图表、图注和术语表；强调专业术语、中文可读性、图片结构与版权边界。Use for professional game-design translation and QA.
Game Design Proposal Writer
DY-2026/GameDesignOS
将调研、概念架构、体验诊断、验证计划、脑图/xmind/系统设计图、已有策划案和生产约束收束为商业游戏策划案、独立游戏设计案、立项评审稿、发行/投资 pitch 或 vertical slice 设计文档。适用于一句话创意先经 game-concept-architect 生成概念契约后再成案、玩法/系统脑图转可落地策划案、审核并改进已有策划案。强调证据边界、受众与商业适配、scope…
Game Design Source Curator
DY-2026/GameDesignOS
用于把游戏设计文章、视频、作者、栏目和网站策展为可持续的本地知识库：包括来源调研、候选筛选、证据门审核、规范入库、增量更新、来源目录、HTML 归档和灵感卡。不要用于一次性摘要、随手推荐、普通新闻浏览或不入库的纯翻译任务。
Game Experience Analyzer
DY-2026/GameDesignOS
用于把游戏截图、本地录屏、PV、买量素材、商店页或视频链接分析为中文证据链诊断报告，包含样本范围门、证据索引、拆解诊断包、模式路由、品类敏感建议、验证计划和可执行优化建议。
Related
Categories
Questions about Game Concept Architect
What does Game Concept Architect do?
将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。. Game Concept Architect is an agent skill from DY-2026/GameDesignOS.
When should I use Game Concept Architect?
Game Concept Architect fits situations like: tasks that involve Game design.
How do I install Game Concept Architect in Claude Code?
Run `npx skills add DY-2026/GameDesignOS --skill game-concept-architect -a claude-code`. Or copy the skill folder (game-concept-architect in DY-2026/GameDesignOS) into .claude/skills/game-concept-architect in your project. Claude Code loads it when a task matches its description.
How do I install Game Concept Architect in Codex?
Run `npx skills add DY-2026/GameDesignOS --skill game-concept-architect -a codex`. Or copy the skill folder (game-concept-architect in DY-2026/GameDesignOS) into .agents/skills/game-concept-architect in your project. Codex loads it when a task matches its description.
Can I use Game Concept Architect 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 DY-2026/GameDesignOS --skill game-concept-architect -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-concept-architect, .gemini/skills/game-concept-architect, .github/skills/game-concept-architect and .opencode/skills/game-concept-architect in your project.
What does Game Concept Architect need to run?
SKILL.md names no scripts, command-line tools or credentials: Game Concept Architect is instructions for the agent only. Compatibility (from SKILL.md): 需要读取用户提供的项目资料；联网调研与写入项目文件仅在任务明确需要时使用。.
Does Game Concept Architect 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 Game Concept Architect 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 Game Concept Architect use?
Game Concept Architect is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Game Concept Architect use?
About 2.1k tokens (SKILL.md is roughly 8.4k 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 10k tokens, read only when the agent opens those files.
What are the alternatives to Game Concept Architect?
Skills that share tags, products or a category with Game Concept Architect: Threejs Gameplay Systems (valkor-ai/loom, 1.2k stars), Godot Gdscript Patterns (925236118/AlphaAgent, 103 stars), Game Asset Spec Writer (Donchitos/Claude-Code-Game-Studios, 26k stars) and Game Build From Design (zenstory-ai/novel-to-game, 841 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Game Concept Architect?
DY-2026 (a GitHub user) maintains it in DY-2026/GameDesignOS, which has 415 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 17, 2026.
Source: DY-2026/GameDesignOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.