AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Game Concept

skill-openaigames-openaigamesdesigner-game-concept · by openaigames

创建或修订游戏概览、核心体验与 Game Pillars;评估已有项目的新功能或方向调整是否影响项目定位,也用于参考作品研究。局部规则和资产修改无需重写概览。

— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-openaigames-openaigamesdesigner-game-concept

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-openaigames-openaigamesdesigner-game-concept)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Game Concept? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Game Concept 项目概览

概览保存当前定位、核心体验、目标玩家和设计支柱,仅在这些承诺改变时修订;不收录每项任务的进度。概览变化需检查策划、美术、技术和验证的消费者;未变化时在变更记录说明依据即可。 跨方向工作按 [变更联动](../game-preproduction/references/dependency-and-change-impact.md) 关联同一变更入口并回写管理摘要;仅安装本 Skill 时沿用项目现有变更记录,缺少管理 Skill 不阻塞本专业工作。

新作概览入口由管理流程先建立,沿用并更新已有内容,不用重复生成。尚未讨论的体验支柱或定位保留候选;入口存在不代表用户确认。

需要澄清核心体验、比较方向或将支柱转为取舍依据时,使用 [体验方向与设计决定](references/experience-to-decisions.md)。保留候选的开放性,实际制作范围放管理记录,具体规则交由策划展开。

新作使用 references/outputs.md 的初期结构。已有项目仅在本轮涉及定位、核心体验或支柱时读取 [现有项目定位与方向变更](references/project-fit.md),沿用其概览位置和结构;不因缺少标准文件而阻塞局部制作。

负责 Game Concept.md 或项目已有的概览;初期创建时使用 [概览交付指导](references/outputs.md)。读取用户原始 idea、明确选择和已有资料。关键体验存在歧义时先反问,说明不同方向的取舍;模型提出的候选不能当成用户已确认的设计。明确的回答形成简短确认摘要,再更新相关正文;用户暂缓的内容保留待讨论。

Game Concept 通常是简短的总结文档,篇幅随信息量调整,让没接触项目的人理解:玩家是谁、身处什么情境、反复做什么、为什么需要取舍、获得什么反馈、为什么想再玩。用一个具体游玩片段把这些关系串起;虚构的示意片段要标明,不冒充试玩实录,不编造任务名、数值或世界设定凑篇幅。

新作进入制作后按 [概览自检](references/outputs.md#概览自检与接续) 补齐有依据的体验关系和决定状态,不能只保留用户原话或已实现功能列表。实现事实不自动变成用户认可的定位;缺少确认的受众、支柱与吸引力保持假设,局部改动仍不重写无关概览。

新建概览包含 Game Pillars:从用户确认的模糊 idea 提炼要保护的体验,并给出支持/冲突的设计选择,作为决策过滤器;候选支柱先交用户讨论,不代替用户确定核心理念。已有项目未整理支柱时不强迫局部任务先补齐。目标受众与吸引力没有调查时写成假设,不能声称已获玩家验证。参考游戏说明借鉴点与差异,不将参考作的所有机制复制为用户需求。

只有制作策略影响项目定位或体验承诺时,概览才保存其摘要并链接美术记录;具体资产、渠道、许可、版本和制作/导入状态由 Art Direction 或已有权威资产清单维护,不在概览重复记账。未知来源在对应美术记录保留取证缺口,不为补概览强行发起选材。首版范围、不做清单和制作条件不放入概览。概览长度随真实内容调整,不以固定字数或标题数量验收。

修订与宿主

从 GDD、美术和技术文档读取已确认依据,发现冲突时指出具体取舍;在授权范围内完成有充分依据的关联修改,新的创作选择保留待决,无关文档保持原状。没有确定美术、引擎或资产渠道时仍可整理已有依据的概览,不编造未知信息。

默认维护 Game Concept.md 或现有概览文件,保存后给出实际链接;项目有 Project Management.md 或同等入口时同步相关文档状态和变更摘要。用户指定结构化宿主时仅修改允许章节,不填未经发生的批准、验证或制作状态。来源区分用户陈述、研究事实、观察与推断,讨论历史不混入专业正文。不生成或启动看板。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.