[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78H810GZGWDHCT3MESF60GH":3,"skill-same:01M78H810GZGWDHCT3MESF60GH":59},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M78H810GZGWDHCT3MESF60GH","pr",null,"撰写 PR body 时使用。","toRolex\u002Frolex-skills","toRolex","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F171526267?v=4","01M78H6W9BVJ5TBK7APN5HFBJF","Rolex","01M78H6WAC60FGNASCYJAJM7VW",1,"MIT","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fpr\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pr\ndescription: \"撰写 PR body 时使用。\"\nmetadata:\n  credits:\n    skill: show-me\n    author: Dex Horthy\n    organisation: Humanlayer\n    url: \"https:\u002F\u002Fgithub.com\u002Fhumanlayer\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fshow-me\u002Fskills\u002Fshow-me\u002FSKILL.md\"\n---\n\n用以下模板撰写 PR body：\n\n```markdown\n## Summary\n\n\u003Cdiagram, diff-sketch, or tree>\n\n## Evidence\n\n- **Before:** \u003Cscreenshot\u002Foutput\u002Ffailing test run>\n  **After:** \u003Cscreenshot\u002Foutput\u002Fpassing test run>\n\n## Merge Danger\n\n**Door:** \u003Cone-way or two-way>\n\n\u003Coptional: description>\n\n**Blast Radius:** \u003Cone-word description>\n\n\u003Coptional: potential ramifications of merge>\n```\n\n## Sections\n\n跳过所有 preamble，行文保持简短。使用 `GLOSSARY.md` 中用户的领域语言。\n\n### Summary\n\n选取能把关键点讲清楚的最小视图。\n\n- 用 pseudocode 展示逻辑或算法：\n\n```text\non(save)\n  if content is unchanged\n    return cached result\n  write new content\n  return fresh result\n```\n\n- 用 call tree 展示运行时控制流：\n\n```text\nsubmitForm\n  createSession\n    persistPrompt\n    launchAgent\n  navigateToSession\n```\n\n- 用 component tree 展示 UI 结构，包含重要的 state 与模块边界：\n\n```text\n\u003CSessionPage> (apps\u002Fexample\u002Fsrc\u002Froutes\u002Fsession.tsx)\n  useSessionEvents()\n  \u003CSessionToolbar>\n    \u003CRunSkillButton> (packages\u002Fui)\n```\n\n- 用浅层 file tree 展示文件职责或大范围重构：\n\n```text\nsrc\u002F\n├── commands\u002F       # parses user actions\n├── sessions\u002F       # owns session state\n└── transport\u002F      # sends API requests\n```\n\n- 用 Mermaid 展示组件交互、控制流或数据流：\n\n```mermaid\nsequenceDiagram\n    participant User\n    participant UI\n    participant Daemon\n    User->>UI: choose command\n    UI->>Daemon: send expanded prompt\n    Daemon-->>UI: stream result\n```\n\n- 当重点在于\"改了什么\"且周围的形态已经存在时，用 `diff`。让 diff 的形态与主题匹配。\n\n组件改动：\n\n```diff\n \u003CSessionPage>\n   useSessionEvents()\n   \u003CSessionToolbar>\n+    \u003CRunSkillButton \u002F>\n   \u003CSessionTimeline>\n+    \u003CSkillResultCard \u002F>\n```\n\n文件布局改动：\n\n```diff\n src\u002F\n ├── commands\u002F\n+│   └── show-me.ts       # expands the slash command\n ├── sessions\u002F\n-└── transport.ts\n+└── transport\u002F\n+    ├── client.ts\n+    └── stream.ts\n```\n\ncall tree 或 call stack 改动：\n\n```diff\n submitForm\n   createSession\n     persistPrompt\n+    expandSkillMention\n     launchAgent\n-  navigateToSession\n+  navigateToSession\n+    subscribeToEvents\n```\n\nstate 或控制流改动：\n\n```diff\n on(save)\n-  write content\n+  if content is unchanged\n+    return cached result\n+  write new content\n+  invalidate cache\n```\n\n- 当大部分内容都是新的、省略上下文会掩盖归属或顺序、或用户需要一个可复制的目标形态时，展示整个代码块：\n\n```ts\nfunction expandSkill(command: string): string {\n  const skillName = command.slice(1);\n  return `use the ${skillName} skill`;\n}\n```\n\n#### Guidance\n\n把每个可视化紧挨着它所支撑的简短文字摆放。只保留回答用户当前问题所需的 calls、files、props、states、boundaries，以及解决当前讨论点所需的选项。\n\n你可以只用其中一种，也可以用几种，但你不太可能全用上。运用判断力，别让用户被淹没。\n\n### Evidence\n\n证明改动确实有效的具体证据。展示 before 与 after。\n\n截图是 S-tier——前提是环境已配置好且改动是视觉性的。\n\n基于执行的证据是 A-tier。测试结果、console 输出。用 pseudocode 展示改动前失败、改动后通过的具体测试。\n\n### Merge Danger\n\n说明这是一扇 one-way door 还是 two-way door。two-way door 可以走回来，one-way door 不行。回滚成本低的 PR 风险更低。涉及破坏性操作或难以逆转决策的改动是 one-way door。\n\nBlast radius 是这个 PR 所引入改动的潜在影响或波及范围。考虑所有可能性。例如布局偏移、对消费方的破坏、移动端响应式等。\n","用以下模板撰写 PR body：\n\n```markdown\n## Summary\n\n\u003Cdiagram, diff-sketch, or tree>\n\n## Evidence\n\n- **Before:** \u003Cscreenshot\u002Foutput\u002Ffailing test run>\n  **After:** \u003Cscreenshot\u002Foutput\u002Fpassing test run>\n\n## Merge Danger\n\n**Door:** \u003Cone-way or two-way>\n\n\u003Coptional: description>\n\n**Blast Radius:** \u003Cone-word description>\n\n\u003Coptional: potential ramifications of merge>\n```\n\n## Sections\n\n跳过所有 preamble，行文保持简短。使用 `GLOSSARY.md` 中用户的领域语言。\n\n### Summary\n\n选取能把关键点讲清楚的最小视图。\n\n- 用 pseudocode 展示逻辑或算法：\n\n```text\non(save)\n  if content is unchanged\n    return cached result\n  write new content\n  return fresh result\n```\n\n- 用 call tree 展示运行时控制流：\n\n```text\nsubmitForm\n  createSession\n    persistPrompt\n    launchAgent\n  navigateToSession\n```\n\n- 用 component tree 展示 UI 结构，包含重要的 state 与模块边界：\n\n```text\n\u003CSessionPage> (apps\u002Fexample\u002Fsrc\u002Froutes\u002Fsession.tsx)\n  useSessionEvents()\n  \u003CSessionToolbar>\n    \u003CRunSkillButton> (packages\u002Fui)\n```\n\n- 用浅层 file tree 展示文件职责或大范围重构：\n\n```text\nsrc\u002F\n├── commands\u002F       # parses user actions\n├── sessions\u002F       # owns session state\n└── transport\u002F      # sends API requests\n```\n\n- 用 Mermaid 展示组件交互、控制流或数据流：\n\n```mermaid\nsequenceDiagram\n    participant User\n    participant UI\n    participant Daemon\n    User->>UI: choose command\n    UI->>Daemon: send expanded prompt\n    Daemon-->>UI: stream result\n```\n\n- 当重点在于\"改了什么\"且周围的形态已经存在时，用 `diff`。让 diff 的形态与主题匹配。\n\n组件改动：\n\n```diff\n \u003CSessionPage>\n   useSessionEvents()\n   \u003CSessionToolbar>\n+    \u003CRunSkillButton \u002F>\n   \u003CSessionTimeline>\n+    \u003CSkillResultCard \u002F>\n```\n\n文件布局改动：\n\n```diff\n src\u002F\n ├── commands\u002F\n+│   └── show-me.ts       # expands the slash command\n ├── sessions\u002F\n-└── transport.ts\n+└── transport\u002F\n+    ├── client.ts\n+    └── stream.ts\n```\n\ncall tree 或 call stack 改动：\n\n```diff\n submitForm\n   createSession\n     persistPrompt\n+    expandSkillMention\n     launchAgent\n-  navigateToSession\n+  navigateToSession\n+    subscribeToEvents\n```\n\nstate 或控制流改动：\n\n```diff\n on(save)\n-  write content\n+  if content is unchanged\n+    return cached result\n+  write new content\n+  invalidate cache\n```\n\n- 当大部分内容都是新的、省略上下文会掩盖归属或顺序、或用户需要一个可复制的目标形态时，展示整个代码块：\n\n```ts\nfunction expandSkill(command: string): string {\n  const skillName = command.slice(1);\n  return `use the ${skillName} skill`;\n}\n```\n\n#### Guidance\n\n把每个可视化紧挨着它所支撑的简短文字摆放。只保留回答用户当前问题所需的 calls、files、props、states、boundaries，以及解决当前讨论点所需的选项。\n\n你可以只用其中一种，也可以用几种，但你不太可能全用上。运用判断力，别让用户被淹没。\n\n### Evidence\n\n证明改动确实有效的具体证据。展示 before 与 after。\n\n截图是 S-tier——前提是环境已配置好且改动是视觉性的。\n\n基于执行的证据是 A-tier。测试结果、console 输出。用 pseudocode 展示改动前失败、改动后通过的具体测试。\n\n### Merge Danger\n\n说明这是一扇 one-way door 还是 two-way door。two-way door 可以走回来，one-way door 不行。回滚成本低的 PR 风险更低。涉及破坏性操作或难以逆转决策的改动是 one-way door。\n\nBlast radius 是这个 PR 所引入改动的潜在影响或波及范围。考虑所有可能性。例如布局偏移、对消费方的破坏、移动端响应式等。\n",{"name":5,"metadata":24,"description":7},{"credits":25},{"url":26,"skill":27,"author":28,"organisation":29},"https:\u002F\u002Fgithub.com\u002Fhumanlayer\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fshow-me\u002Fskills\u002Fshow-me\u002FSKILL.md","show-me","Dex Horthy","Humanlayer","main","5648606410e64c6ebad383fa37b866fcd14718cf","skills\u002Fengineering\u002Fpr",0,"https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills","https:\u002F\u002Fgithub.com\u002FtoRolex","luolie3@mail2.sysu.edu.cn","I'm Luo Lie from SYSU. Mathematics-trained builder for agentic AI systems and real-world products.","2026-11-03 15:28:15",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add toRolex\u002Frolex-skills --skill pr",{"tool":45,"command":46},"bunx","bunx skills add toRolex\u002Frolex-skills --skill pr",{"tool":48,"command":49},"pnpm","pnpm dlx skills add toRolex\u002Frolex-skills --skill pr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fpr\u002FSKILL.md",true,[53],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"agents\u002Fopenai.yaml","REFERENCE","参考文档",93,"https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fpr\u002Fagents\u002Fopenai.yaml",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M78HA978AVPWGFE3PR9RNJ9G","writing-great-skills","Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M78HA7737MNQ4411A7SZWPJQ","writing-for-agents","覆盖创建、修改与审核 agent 指令规则、路由及指针文档（如 skill、AGENTS.md、CLAUDE.md）。","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M78HA62NC1NZNAEZ26784495","wait-what","停下。上一条消息没有说清楚：重新讲一遍。","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"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},"01M78HA4NX5KBJ7WQ69SR25QHW","to-questionnaire","把一个你无法完全回答的决策，变成一个让其他人填写的问题单。","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fto-questionnaire\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},"01M78HA2RTESFTRTNA7ZZNVVXS","teach-me","在教学工作区内教授用户一项新技能或概念。","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fteach-me\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M78HA187DQB10VDJ4G89F540","handoff","将当前对话压缩为 handoff 文档，供另一个 agent 接续。","https:\u002F\u002Fgithub.com\u002FtoRolex\u002Frolex-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fhandoff\u002FSKILL.md",[],[]]