agentleFS
eyeixeyeix/skills/prototype/SKILL.md

prototype

Skill1 starsChanged 30 days agoMITView on GitHub

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

194 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

Files
SKILL.md

原型

原型是回答一个问题的抛弃型代码。问题决定形状。

选分支

用用户的提示、上下文代码判断要回答哪个问题,用户在场拿不准就问:

  • "这个逻辑 / 状态模型对不对?" → 读 LOGIC.md。产出单个可分享的 HTML 文件(自由按钮 + 分页引导场景),把状态机推过那些纸上难推理的案例,非开发者也能上手;
  • "这该长什么样?" → 读 UI.md。在同一路由上生成多个截然不同的 UI 变体,URL 参数切换,底部浮动条选择。

两个分支的产物完全不同,选错就白做。问题真模糊且用户不在场时,按上下文代码选更贴合的一支(后端模块 → 逻辑;页面或组件 → UI),并在原型顶部声明这个假设。

两个分支共同的规则

  1. 从第一天起就是抛弃型的,并明确标记。原型代码放在它真正服务的位置旁(被原型化的模块或页面边上),上下文一目了然;命名让随便哪个读者一眼看出它是原型,不是产品。抛弃型 UI 路由遵守项目既有路由约定,不发明新的顶层结构;
  2. 一条命令可运行。UI 原型从项目任务器一条命令启动(pnpm <name>、python <path>、bun <path> 等);逻辑演示是双击即开的单个 HTML。启动不需要思考;
  3. 默认不持久化。状态在内存里。持久化是原型要检验的东西,不是它依赖的东西。问题真涉及数据库时,用 scratch 库或明确标注 "PROTOTYPE, 可删" 的本地文件;
  4. 跳过打磨。不写测试,不做超出"能运行"的错误处理,不建抽象。目的是快速学到东西;
  5. 暴露状态。每次操作后(逻辑)或每次变体切换时(UI),打印或渲染完整的相关状态,让用户看见什么变了;
  6. 完成后捕获。验证过的决策折进真实代码,原型本身作为一手来源捕获:提交到 main 之外的抛弃型分支(prototype/<名字>),在任务文档或工单上留下指向该分支的上下文指针。答案本身(结论与它解决的问题)也记进工单或 commit。main 只保留验证过的决策。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.