[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EEPEYZ09WYSPFN0WEYTTJ8":3,"skill-same:01M7EEPEYZ09WYSPFN0WEYTTJ8":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EEPEYZ09WYSPFN0WEYTTJ8","prototype",null,"构建一次性原型来回答一个设计问题。当用户想验证某个状态模型或逻辑感觉对不对，或想探索 UI 应该长什么样时使用。","luestr\u002Fskills","luestr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F152216177?v=4","01M7EEH85TQXC26ZZTNFPWV5E9","可莉","01M7EEH86EYXTVTCERP22VMFXX",94,"MIT","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fmattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prototype\ndescription: 构建一次性原型来回答一个设计问题。当用户想验证某个状态模型或逻辑感觉对不对，或想探索 UI 应该长什么样时使用。\nmetadata:\n  language: zh-CN\n---\n\n# 原型\n\n原型是**回答某个问题的一次性代码**。问题决定它的形态。\n\n## 选一条分支\n\n用用户的提示词、周围的代码，或者在用户就在旁边时直接问，判断正在回答的是哪个问题：\n\n- **“这套逻辑／状态模型感觉对吗？”** → [LOGIC.md](LOGIC.md)。构建一个可分享的单一 HTML 文件（自由试玩按钮加标签页式引导演练），把状态机推进那些纸上难以推理的场景，并且非开发者也能操作。\n- **“这个应该长什么样？”** → [UI.md](UI.md)。在单个路由上生成几个截然不同的 UI 变体，通过 URL 查询参数和悬浮底栏切换。\n\n两条分支产出的东西差别很大，选错会浪费整个原型。如果问题确实含糊、又联系不上用户，就默认选与周围代码更匹配的那条分支（后端模块 → 逻辑；页面或组件 → UI），并在原型顶部说明这一假设。\n\n## 两条分支都适用的规则\n\n1. **从第一天起就是一次性的（用完即弃），并且明确标注。** 把原型代码放在它真正会被使用的位置附近（紧挨着它所针对的模块或页面），让上下文一目了然；但命名要让人随便一看就知道这是原型，不是生产代码。对于一次性的 UI 路由，遵守项目已有的路由约定；不要发明新的顶层结构。\n2. **运行起来毫不费力。** UI 原型从项目任务运行器里的一条命令启动：`pnpm \u003Cname>`、`python \u003Cpath>`、`bun \u003Cpath>` 等。逻辑演示则是用户双击打开的一个 HTML 文件。无论哪种，启动都不需要动脑。\n3. **默认不做持久化。** 状态存在内存里。持久化是原型要_检验_的东西，而不是它应当依赖的东西。如果问题明确涉及数据库，就用一个临时 DB，或者用一个名字明确写着 “PROTOTYPE, wipe me” 的本地文件。\n4. **跳过打磨。** 不要测试，不要写超出让原型_能跑起来_所必需的错误处理，不要抽象。重点是把东西快速学会。\n5. **把状态暴露出来。** 每次操作之后（逻辑）或每次切换变体时（UI），打印或渲染完整的相关状态，让用户看到变了什么。\n6. **收尾时把它留存下来。** 把验证过的决策并入真实代码，然后把原型本身作为**一手资料**留存：提交到一个一次性分支上，不要进 main，并在实现 issue 上留一个指向该分支的上下文指针。答案也要留下来（结论以及它敲定的问题），记在 issue 或某次提交里。main 分支只保留验证过的决策。\n","# 原型\n\n原型是**回答某个问题的一次性代码**。问题决定它的形态。\n\n## 选一条分支\n\n用用户的提示词、周围的代码，或者在用户就在旁边时直接问，判断正在回答的是哪个问题：\n\n- **“这套逻辑／状态模型感觉对吗？”** → [LOGIC.md](LOGIC.md)。构建一个可分享的单一 HTML 文件（自由试玩按钮加标签页式引导演练），把状态机推进那些纸上难以推理的场景，并且非开发者也能操作。\n- **“这个应该长什么样？”** → [UI.md](UI.md)。在单个路由上生成几个截然不同的 UI 变体，通过 URL 查询参数和悬浮底栏切换。\n\n两条分支产出的东西差别很大，选错会浪费整个原型。如果问题确实含糊、又联系不上用户，就默认选与周围代码更匹配的那条分支（后端模块 → 逻辑；页面或组件 → UI），并在原型顶部说明这一假设。\n\n## 两条分支都适用的规则\n\n1. **从第一天起就是一次性的（用完即弃），并且明确标注。** 把原型代码放在它真正会被使用的位置附近（紧挨着它所针对的模块或页面），让上下文一目了然；但命名要让人随便一看就知道这是原型，不是生产代码。对于一次性的 UI 路由，遵守项目已有的路由约定；不要发明新的顶层结构。\n2. **运行起来毫不费力。** UI 原型从项目任务运行器里的一条命令启动：`pnpm \u003Cname>`、`python \u003Cpath>`、`bun \u003Cpath>` 等。逻辑演示则是用户双击打开的一个 HTML 文件。无论哪种，启动都不需要动脑。\n3. **默认不做持久化。** 状态存在内存里。持久化是原型要_检验_的东西，而不是它应当依赖的东西。如果问题明确涉及数据库，就用一个临时 DB，或者用一个名字明确写着 “PROTOTYPE, wipe me” 的本地文件。\n4. **跳过打磨。** 不要测试，不要写超出让原型_能跑起来_所必需的错误处理，不要抽象。重点是把东西快速学会。\n5. **把状态暴露出来。** 每次操作之后（逻辑）或每次切换变体时（UI），打印或渲染完整的相关状态，让用户看到变了什么。\n6. **收尾时把它留存下来。** 把验证过的决策并入真实代码，然后把原型本身作为**一手资料**留存：提交到一个一次性分支上，不要进 main，并在实现 issue 上留一个指向该分支的上下文指针。答案也要留下来（结论以及它敲定的问题），记在 issue 或某次提交里。main 分支只保留验证过的决策。\n",{"name":5,"metadata":24,"description":7},{"language":25},"zh-CN","main","e755255990a0250bbae1a416cea9388f10b6bf6a","mattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype",1,"https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills","https:\u002F\u002Fgithub.com\u002Fluestr","2026-11-14 01:15:26",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add luestr\u002Fskills --skill prototype",{"tool":39,"command":40},"bunx","bunx skills add luestr\u002Fskills --skill prototype",{"tool":42,"command":43},"pnpm","pnpm dlx skills add luestr\u002Fskills --skill prototype","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fmattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",96,"https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fmattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"LOGIC.md",5778,"https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fmattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype\u002FLOGIC.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"UI.md",6689,"https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fmattpocock\u002Fzh-CN\u002Fengineering\u002Fprototype\u002FUI.md",[62,69,75,82,88,95],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7EESZM2QJKA5M0QS4M0WNGA","write-ublock-origin-filters","完整的 uBlock Origin (uBO) 静态过滤语法参考。编写 uBlock Origin 自定义过滤规则时使用此技能，涵盖广告拦截、隐私保护或内容过滤。包含基础网络过滤模式（||、*、^、|）、所有网络过滤选项（$domain、$third-party、$important、$redirect、$removeparam、$csp、$replace、$header、$method、$denyallow、$badfilter、$all 等）、内容类型选项（$script、$image、$stylesheet、$font、$media、$xhr、$popup、$document、$frame 等）、元素隐藏规则（## 选择器、实体匹配、主机名正则）、过程式元素隐藏过滤器（:has、:has-text、:matches-css、:upward、:xpath、:matches-path、:watch-attr 等）、动作操作符（:remove、:style、:remove-attr、:remove-class）、HTML 过滤器（##^）、响应头过滤（##^responseheader）、脚本注入（##+js()）以及预处理指令（!#include、!#if）。当用户提到 uBlock Origin 过滤规则、uBO 语法、广告拦截规则、元素隐藏规则、过程式选择器、脚本注入或希望编写\u002F调试任何 uBO 兼容过滤列表时触发。即使用户只是在编写或调试 uBlock Origin 过滤规则、创建自定义过滤列表或从 AdBlock Plus\u002FAdGuard 迁移过滤规则到 uBO，也应使用此技能。","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-ublock-origin-filters\u002Fzh-CN\u002Fwrite-ublock-origin-filters\u002FSKILL.md",[],[],{"skillNo":70,"name":64,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EESN8NBTRJE793B87NBGA5","Complete uBlock Origin (uBO) static filter reference. Use this skill when writing or debugging uBO custom filters or filter lists for ad blocking, privacy or content filtering, or when migrating filters from AdBlock Plus\u002FAdGuard. Covers network patterns (||, *, ^, |) and options ($domain, $third-party, $important, $redirect, $removeparam, $csp, $replace, $header, $method, $badfilter, $all), content-type options ($script, $image, $stylesheet, $font, $media, $xhr, $popup, $document, $frame), cosmetic filters (##, CSS selectors, entity matching), procedural filters (:has, :has-text, :matches-css, :upward, :xpath, :matches-path, :watch-attr), action operators (:remove, :style, :remove-attr), HTML filters (##^), response-header filtering (##^responseheader), scriptlet injection (##+js()), and pre-parsing directives (!#include, !#if). Trigger whenever the user mentions uBO syntax, ad blocking rules, element hiding, procedural selectors, scriptlet injection, or a uBO-compatible filter list.","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-ublock-origin-filters\u002Fen-US\u002Fwrite-ublock-origin-filters\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EESH94GM6NWB3JAFRH7D8S","write-tampermonkey-scripts","引导 AI 代理规划、编写、调试、测试和维护 Tampermonkey 用户脚本。当用户请求用户脚本、浏览器页面自动化、DOM 增强、Tampermonkey 元数据、GM_* API、@match、@grant、@run-at、@connect、跨源请求、SPA 页面集成或脚本注入任务时使用此技能，即使用户没有明确提及 Tampermonkey。","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-tampermonkey-scripts\u002Fzh-CN\u002Fwrite-tampermonkey-scripts\u002FSKILL.md",[],[],{"skillNo":83,"name":77,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EESCKXFQ793C4TCKSV0GZ1","Guide an AI agent through planning, writing, debugging, testing, and maintaining Tampermonkey userscripts. Use this skill whenever a user asks for a userscript, browser-page automation, DOM enhancement, Tampermonkey metadata, GM_* API, @match, @grant, @run-at, @connect, cross-origin request, SPA page integration, or script injection task, even when Tampermonkey is not named explicitly.","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-tampermonkey-scripts\u002Fen-US\u002Fwrite-tampermonkey-scripts\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7EES6SHP4F6DTQYRJ944KMR","write-adguard-filters","编写 AdGuard 自定义过滤规则时使用此技能。涵盖基本规则语法、所有修饰符（$domain\u002F$third-party\u002F$important\u002F$redirect\u002F$replace\u002F$removeparam\u002F$cookie\u002F$csp 等）、外观规则（元素隐藏\u002FCSS\u002FExtended CSS 选择器）、HTML 过滤、JavaScript\u002F脚本片段规则、非基本规则修饰符、预处理器指令和调试技巧。当用户提及 AdGuard 过滤规则、广告拦截规则语法、过滤器列表编写、ABP 语法兼容、元素隐藏规则、Extended CSS 选择器（:has\u002F:contains\u002F:matches-css 等）时触发。即使用户只是在编写或调试任何类型的广告过滤规则，也应使用此技能。","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-adguard-filters\u002Fzh-CN\u002Fwrite-adguard-filters\u002FSKILL.md",[],[],{"skillNo":96,"name":90,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7EERZ661557QAD511EBSCCK","Complete AdGuard filtering rules syntax reference. Use this skill when writing AdGuard custom filters. Covers basic rule syntax, all modifiers ($domain\u002F$third-party\u002F$important\u002F$redirect\u002F$replace\u002F$removeparam\u002F$cookie\u002F$csp etc.), cosmetic rules (element hiding\u002FCSS\u002FExtended CSS selectors), HTML filtering, JavaScript\u002Fscriptlet rules, non-basic rule modifiers, preprocessor directives, and debugging. Trigger when user mentions AdGuard filtering rules, ad blocking rule syntax, filter list authoring, ABP syntax compatibility, element hiding rules, Extended CSS selectors (:has\u002F:contains\u002F:matches-css etc.). Use this skill even when the user is just writing or debugging any type of ad filtering rules.","https:\u002F\u002Fgithub.com\u002Fluestr\u002Fskills\u002Fblob\u002Fmain\u002Fwrite-adguard-filters\u002Fen-US\u002Fwrite-adguard-filters\u002FSKILL.md",[],[]]