Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DY-2026/GameDesignOS --skill game-concept-architectgit clone --depth 1 https://github.com/DY-2026/GameDesignOSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dy-2026/gamedesignos/game-concept-architect)<a href="https://agentmods.dev/skills/dy-2026/gamedesignos/game-concept-architect"><img src="https://agentmods.dev/badge/skills/dy-2026/gamedesignos/game-concept-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dy-2026/gamedesignos/game-concept-architect"><img src="https://agentmods.dev/badge/skills/dy-2026/gamedesignos/game-concept-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.03598 |
| Opus 5 | $0.00044 | $0.01799 |
| Sonnet 5 | $0.00018 | $0.00720 |
| Haiku 4.5 | $0.00009 | $0.00360 |
Grade A, and why
game-concept-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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。
What ships with it
50 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 482 B
- assets/clockwork-garden-defense-key-art.png 2647 KB
- evals/behavior_evals.json 402 B
- evals/evals.json 7.8 KB
- evals/negative_cases.md 7.3 KB
- evals/rubric.yaml 5.3 KB
- evals/synthetic_outputs.json 488 B
- examples/clockwork-garden-defense-illustrated.md 13 KB
- examples/clockwork-garden-defense.md 5.5 KB
- examples/dream-postman-card-adventure.md 5.5 KB
- examples/README.md 2.1 KB
- examples/tiny-crew-space-salvage.md 5.7 KB
- README.md 8.5 KB
- references/concept-seed-extraction.zh-CN.md 3.2 KB
- references/core-loop-expansion.zh-CN.md 2.3 KB
- references/design-nucleus-options.zh-CN.md 2.7 KB
- references/external-feasibility-scan.zh-CN.md 1.8 KB
- references/game-dissection-lens.zh-CN.md 7.6 KB
- references/genre-fit-matrix.zh-CN.md 3.2 KB
- references/platform-business-fit.zh-CN.md 2.9 KB
- references/player-promise-framework.zh-CN.md 2.5 KB
- references/production-feasibility.zh-CN.md 3.5 KB
- references/production-profile-gate.zh-CN.md 2.1 KB
- references/prototype-validation-gate.zh-CN.md 2.4 KB
- references/reference-game-boundary.zh-CN.md 2.0 KB
- references/scope-gate.zh-CN.md 2.3 KB
- references/voi-feasibility-gate.zh-CN.md 2.6 KB
- templates/action-goal-alignment.md 932 B
- templates/assumption-ledger.md 1.2 KB
- templates/audience-desire-map.md 882 B
- templates/concept-brief.schema.json 4.0 KB
- templates/content-flow-plan.md 993 B
- templates/design-nucleus-options.md 1.0 KB
- templates/feasibility-scan.md 1.4 KB
- templates/feature-priority-matrix.md 1.0 KB
- templates/full-design-brief.md 4.4 KB
- templates/idea-triage.md 1.9 KB
- templates/one-page-pitch.md 2.3 KB
- templates/playable-theme-map.md 958 B
- templates/player-promise-contract.md 1.2 KB
- templates/player-promise-contract.schema.json 1.8 KB
- templates/player-verb-inventory.md 1000 B
- templates/production-budget-snapshot.md 1.1 KB
- templates/production-profile.md 1.2 KB
- templates/reference-game-boundary.md 955 B
- templates/risk-register.md 1.1 KB
- templates/system-dynamics-map.md 745 B
- templates/uncertainty-calibration.md 1.5 KB
- templates/validation-plan.md 972 B
- templates/vertical-slice-plan.md 3.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 294 lines · 89 tokens per session scan A c6e286e065cb
game-concept-architect is a skill published in the GitHub repository DY-2026/GameDesignOS (385 stars, last pushed 24d ago), licensed MIT. It adds 89 tokens to every session and 3,598 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aigd
AIGD (AI Game Design) main entry / orchestrator. Use this when the user wants to start a game project from scratch, is unsure which phase to use, wants to survey or advance the entire development pipeline, or needs to maintain the project spine (project charter / manifest). This skill only does "read the spine → judge…
aigd-handoff
AIGD Phase 4 · finalize and generate the handoff package. Use this when, after a system is finalized in playtesting, you want to generate the interface contract, acceptance cases, (as needed) art/client/server docs, and the designer-facing acceptance checklist. Produces platform-agnostic handoff artifacts that…
aigd-ui-capture
AIGD · UI screenshot → UI DSL (knowledge-base capture / tool 1). Use this when you want to turn a game UI screenshot (a competitor's or your own) into structured md (type/hierarchy/geometry/interaction/state), so uirender.py can restore it to a wireframe and it can be accumulated into the patterns/UI-paradigm…
aigd-sync
AIGD cross-cutting action · sync-back integration (a non-linear "last step", triggered after every system's handoff). Use this when, once a system is settled, you need to update the global spec, the overall html prototype (integration demo), the implementation master guide (handoff-package entry point), or mark…
aigd-concept
AIGD Phase 1 · brainstorming & top-level design. Use this when you want to set the concept for a new game, fix the core loop / platform / target users, or split the game into a system list + dependency graph and start the project spine. Produces / revises the project charter + manifest (system list). Part of the aigd…
aigd-iterate
AIGD Phase 3 · playtest iteration. Use this when, after the user playtests the prototype, they want to optimize the rules or change the config table (can be run repeatedly). Only touches the "cheap" artifacts — rules / config / prototype — not the contract / acceptance (those are produced after finalization). Part of…