[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M731VTJGWHNZ68DC5STV34G3":3,"skill-same:01M731VTJGWHNZ68DC5STV34G3":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M731VTJGWHNZ68DC5STV34G3","code-tour",null,"创建 CodeTour `.tour` 文件——针对特定角色的、带有真实文件和行锚点的逐步演练。用于入职引导、架构演练、PR 演练、RCA 演练以及结构化的“解释其工作原理”请求。","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcode-tour\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: code-tour\ndescription: 创建 CodeTour `.tour` 文件——针对特定角色的、带有真实文件和行锚点的逐步演练。用于入职引导、架构演练、PR 演练、RCA 演练以及结构化的“解释其工作原理”请求。\norigin: ECC\n---\n\n# 代码导览\n\n创建 **CodeTour** `.tour`文件，用于代码库导览，可直接打开真实文件并定位到指定行范围。导览文件存放在`.tours\u002F` 目录中，专为 CodeTour 格式设计，而非临时性的 Markdown 笔记。\n\n一个好的导览应针对特定读者讲述一个故事：\n\n* 他们正在查看什么\n* 为什么重要\n* 接下来应该遵循什么路径\n\n仅创建 `.tour` JSON 文件。不要在此技能范围内修改源代码。\n\n## 何时使用\n\n在以下情况下使用此技能：\n\n* 用户请求代码导览、入职导览、架构导览或 PR 导览\n* 用户说“解释 X 如何工作”，并希望获得可重用的引导式产物\n* 用户希望为新工程师或审阅者提供上手路径\n* 相比平铺直叙的摘要，引导式序列更适合该任务\n\n示例：\n\n* 新维护者入职\n* 单个服务或包的架构导览\n* 锚定到变更文件的 PR 审查导览\n* 展示故障路径的根本原因分析导览\n* 信任边界和关键检查的安全审查导览\n\n## 何时不使用\n\n| 不使用代码导览的情况 | 使用 |\n| --- | --- |\n| 在聊天中一次性解释就足够了 | 直接回答 |\n| 用户想要散文式文档，而不是 `.tour`产物 |`documentation-lookup` 或仓库文档编辑 |\n| 任务是实现或重构 | 执行实现工作 |\n| 任务是没有导览产物的广泛代码库入职 | `codebase-onboarding` |\n\n## 工作流程\n\n### 1. 探索\n\n在编写任何内容之前探索仓库：\n\n* README 和包\u002F应用入口点\n* 文件夹结构\n* 相关配置文件\n* 如果导览聚焦于 PR，则查看变更的文件\n\n在理解代码结构之前，不要开始编写步骤。\n\n### 2. 推断读者\n\n根据请求确定角色和深度。\n\n| 请求形式 | 角色 | 建议深度 |\n| --- | --- | --- |\n| \"入职\"，\"新成员\" | `new-joiner` | 9-13 步 |\n| \"快速导览\"，\"快速了解\" | `vibecoder` | 5-8 步 |\n| \"架构\" | `architect` | 14-18 步 |\n| \"导览此 PR\" | `pr-reviewer` | 7-11 步 |\n| \"为什么这个出错了\" | `rca-investigator` | 7-11 步 |\n| \"安全审查\" | `security-reviewer` | 7-11 步 |\n| \"解释此功能如何工作\" | `feature-explainer` | 7-11 步 |\n| \"调试此路径\" | `bug-fixer` | 7-11 步 |\n\n### 3. 读取并验证锚点\n\n每个文件路径和行锚点必须是真实的：\n\n* 确认文件存在\n* 确认行号在范围内\n* 如果使用选区，验证确切的代码块\n* 如果文件易变，优先使用基于模式的锚点\n\n切勿猜测行号。\n\n### 4. 编写 `.tour`\n\n写入：\n\n```text\n.tours\u002F\u003Cpersona>-\u003Cfocus>.tour\n```\n\n保持路径确定且可读。\n\n### 5. 验证\n\n在完成之前：\n\n* 每个引用的路径都存在\n* 每行或每个选区都有效\n* 第一步锚定到真实文件或目录\n* 导览讲述连贯的故事，而非罗列文件\n\n## 步骤类型\n\n### 内容\n\n谨慎使用，通常仅用于结束步骤：\n\n```json\n{ \"title\": \"Next Steps\", \"description\": \"You can now trace the request path end to end.\" }\n```\n\n不要将第一步设为纯内容。\n\n### 目录\n\n用于引导读者了解模块：\n\n```json\n{ \"directory\": \"src\u002Fservices\", \"title\": \"Service Layer\", \"description\": \"The core orchestration logic lives here.\" }\n```\n\n### 文件 + 行\n\n这是默认步骤类型：\n\n```json\n{ \"file\": \"src\u002Fauth\u002Fmiddleware.ts\", \"line\": 42, \"title\": \"Auth Gate\", \"description\": \"Every protected request passes here first.\" }\n```\n\n### 选区\n\n当某个代码块比整个文件更重要时使用：\n\n```json\n{\n  \"file\": \"src\u002Fcore\u002Fpipeline.ts\",\n  \"selection\": {\n    \"start\": { \"line\": 15, \"character\": 0 },\n    \"end\": { \"line\": 34, \"character\": 0 }\n  },\n  \"title\": \"Request Pipeline\",\n  \"description\": \"This block wires validation, auth, and downstream execution.\"\n}\n```\n\n### 模式\n\n当精确行号可能发生变化时使用：\n\n```json\n{ \"file\": \"src\u002Fapp.ts\", \"pattern\": \"export default class App\", \"title\": \"Application Entry\" }\n```\n\n### URI\n\n在需要时用于 PR、问题或文档：\n\n```json\n{ \"uri\": \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F456\", \"title\": \"The PR\" }\n```\n\n## 编写规则：SMIG\n\n每个描述应回答：\n\n* **情境**：读者正在查看什么\n* **机制**：它是如何工作的\n* **影响**：为什么对此角色重要\n* **陷阱**：聪明的读者可能会错过什么\n\n保持描述简洁、具体，并基于实际代码。\n\n## 叙事结构\n\n除非任务明确需要不同结构，否则使用此弧线：\n\n1. 定位\n2. 模块地图\n3. 核心执行路径\n4. 边缘情况或陷阱\n5. 结束 \u002F 下一步\n\n导览应感觉像一条路径，而非清单。\n\n## 示例\n\n```json\n{\n  \"$schema\": \"https:\u002F\u002Faka.ms\u002Fcodetour-schema\",\n  \"title\": \"API Service Tour\",\n  \"description\": \"Walkthrough of the request path for the payments service.\",\n  \"ref\": \"main\",\n  \"steps\": [\n    {\n      \"directory\": \"src\",\n      \"title\": \"Source Root\",\n      \"description\": \"All runtime code for the service starts here.\"\n    },\n    {\n      \"file\": \"src\u002Fserver.ts\",\n      \"line\": 12,\n      \"title\": \"Entry Point\",\n      \"description\": \"The server boots here and wires middleware before any route is reached.\"\n    },\n    {\n      \"file\": \"src\u002Froutes\u002Fpayments.ts\",\n      \"line\": 8,\n      \"title\": \"Payment Routes\",\n      \"description\": \"Every payments request enters through this router before hitting service logic.\"\n    },\n    {\n      \"title\": \"Next Steps\",\n      \"description\": \"You can now follow any payment request end to end with the main anchors in place.\"\n    }\n  ]\n}\n```\n\n## 反模式\n\n| 反模式 | 修复 |\n| --- | --- |\n| 平铺直叙的文件列表 | 讲述一个步骤间有依赖关系的故事 |\n| 通用描述 | 指明具体的代码路径或模式 |\n| 猜测的锚点 | 先验证每个文件和行 |\n| 快速导览步骤过多 | 果断精简 |\n| 第一步是纯内容 | 将第一步锚定到真实文件或目录 |\n| 角色不匹配 | 为实际读者编写，而非通用工程师 |\n\n## 最佳实践\n\n* 步骤数量与仓库大小和角色深度成比例\n* 使用目录步骤进行定位，文件步骤用于实质内容\n* 对于 PR 导览，首先覆盖变更的文件\n* 对于单体仓库，将范围限定在相关包，而非导览所有内容\n* 以读者现在可以做什么来结束，而非总结\n\n## 相关技能\n\n* `codebase-onboarding`\n* `coding-standards`\n* `council`\n* 官方上游格式：`microsoft\u002Fcodetour`\n","# 代码导览\n\n创建 **CodeTour** `.tour`文件，用于代码库导览，可直接打开真实文件并定位到指定行范围。导览文件存放在`.tours\u002F` 目录中，专为 CodeTour 格式设计，而非临时性的 Markdown 笔记。\n\n一个好的导览应针对特定读者讲述一个故事：\n\n* 他们正在查看什么\n* 为什么重要\n* 接下来应该遵循什么路径\n\n仅创建 `.tour` JSON 文件。不要在此技能范围内修改源代码。\n\n## 何时使用\n\n在以下情况下使用此技能：\n\n* 用户请求代码导览、入职导览、架构导览或 PR 导览\n* 用户说“解释 X 如何工作”，并希望获得可重用的引导式产物\n* 用户希望为新工程师或审阅者提供上手路径\n* 相比平铺直叙的摘要，引导式序列更适合该任务\n\n示例：\n\n* 新维护者入职\n* 单个服务或包的架构导览\n* 锚定到变更文件的 PR 审查导览\n* 展示故障路径的根本原因分析导览\n* 信任边界和关键检查的安全审查导览\n\n## 何时不使用\n\n| 不使用代码导览的情况 | 使用 |\n| --- | --- |\n| 在聊天中一次性解释就足够了 | 直接回答 |\n| 用户想要散文式文档，而不是 `.tour`产物 |`documentation-lookup` 或仓库文档编辑 |\n| 任务是实现或重构 | 执行实现工作 |\n| 任务是没有导览产物的广泛代码库入职 | `codebase-onboarding` |\n\n## 工作流程\n\n### 1. 探索\n\n在编写任何内容之前探索仓库：\n\n* README 和包\u002F应用入口点\n* 文件夹结构\n* 相关配置文件\n* 如果导览聚焦于 PR，则查看变更的文件\n\n在理解代码结构之前，不要开始编写步骤。\n\n### 2. 推断读者\n\n根据请求确定角色和深度。\n\n| 请求形式 | 角色 | 建议深度 |\n| --- | --- | --- |\n| \"入职\"，\"新成员\" | `new-joiner` | 9-13 步 |\n| \"快速导览\"，\"快速了解\" | `vibecoder` | 5-8 步 |\n| \"架构\" | `architect` | 14-18 步 |\n| \"导览此 PR\" | `pr-reviewer` | 7-11 步 |\n| \"为什么这个出错了\" | `rca-investigator` | 7-11 步 |\n| \"安全审查\" | `security-reviewer` | 7-11 步 |\n| \"解释此功能如何工作\" | `feature-explainer` | 7-11 步 |\n| \"调试此路径\" | `bug-fixer` | 7-11 步 |\n\n### 3. 读取并验证锚点\n\n每个文件路径和行锚点必须是真实的：\n\n* 确认文件存在\n* 确认行号在范围内\n* 如果使用选区，验证确切的代码块\n* 如果文件易变，优先使用基于模式的锚点\n\n切勿猜测行号。\n\n### 4. 编写 `.tour`\n\n写入：\n\n```text\n.tours\u002F\u003Cpersona>-\u003Cfocus>.tour\n```\n\n保持路径确定且可读。\n\n### 5. 验证\n\n在完成之前：\n\n* 每个引用的路径都存在\n* 每行或每个选区都有效\n* 第一步锚定到真实文件或目录\n* 导览讲述连贯的故事，而非罗列文件\n\n## 步骤类型\n\n### 内容\n\n谨慎使用，通常仅用于结束步骤：\n\n```json\n{ \"title\": \"Next Steps\", \"description\": \"You can now trace the request path end to end.\" }\n```\n\n不要将第一步设为纯内容。\n\n### 目录\n\n用于引导读者了解模块：\n\n```json\n{ \"directory\": \"src\u002Fservices\", \"title\": \"Service Layer\", \"description\": \"The core orchestration logic lives here.\" }\n```\n\n### 文件 + 行\n\n这是默认步骤类型：\n\n```json\n{ \"file\": \"src\u002Fauth\u002Fmiddleware.ts\", \"line\": 42, \"title\": \"Auth Gate\", \"description\": \"Every protected request passes here first.\" }\n```\n\n### 选区\n\n当某个代码块比整个文件更重要时使用：\n\n```json\n{\n  \"file\": \"src\u002Fcore\u002Fpipeline.ts\",\n  \"selection\": {\n    \"start\": { \"line\": 15, \"character\": 0 },\n    \"end\": { \"line\": 34, \"character\": 0 }\n  },\n  \"title\": \"Request Pipeline\",\n  \"description\": \"This block wires validation, auth, and downstream execution.\"\n}\n```\n\n### 模式\n\n当精确行号可能发生变化时使用：\n\n```json\n{ \"file\": \"src\u002Fapp.ts\", \"pattern\": \"export default class App\", \"title\": \"Application Entry\" }\n```\n\n### URI\n\n在需要时用于 PR、问题或文档：\n\n```json\n{ \"uri\": \"https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F456\", \"title\": \"The PR\" }\n```\n\n## 编写规则：SMIG\n\n每个描述应回答：\n\n* **情境**：读者正在查看什么\n* **机制**：它是如何工作的\n* **影响**：为什么对此角色重要\n* **陷阱**：聪明的读者可能会错过什么\n\n保持描述简洁、具体，并基于实际代码。\n\n## 叙事结构\n\n除非任务明确需要不同结构，否则使用此弧线：\n\n1. 定位\n2. 模块地图\n3. 核心执行路径\n4. 边缘情况或陷阱\n5. 结束 \u002F 下一步\n\n导览应感觉像一条路径，而非清单。\n\n## 示例\n\n```json\n{\n  \"$schema\": \"https:\u002F\u002Faka.ms\u002Fcodetour-schema\",\n  \"title\": \"API Service Tour\",\n  \"description\": \"Walkthrough of the request path for the payments service.\",\n  \"ref\": \"main\",\n  \"steps\": [\n    {\n      \"directory\": \"src\",\n      \"title\": \"Source Root\",\n      \"description\": \"All runtime code for the service starts here.\"\n    },\n    {\n      \"file\": \"src\u002Fserver.ts\",\n      \"line\": 12,\n      \"title\": \"Entry Point\",\n      \"description\": \"The server boots here and wires middleware before any route is reached.\"\n    },\n    {\n      \"file\": \"src\u002Froutes\u002Fpayments.ts\",\n      \"line\": 8,\n      \"title\": \"Payment Routes\",\n      \"description\": \"Every payments request enters through this router before hitting service logic.\"\n    },\n    {\n      \"title\": \"Next Steps\",\n      \"description\": \"You can now follow any payment request end to end with the main anchors in place.\"\n    }\n  ]\n}\n```\n\n## 反模式\n\n| 反模式 | 修复 |\n| --- | --- |\n| 平铺直叙的文件列表 | 讲述一个步骤间有依赖关系的故事 |\n| 通用描述 | 指明具体的代码路径或模式 |\n| 猜测的锚点 | 先验证每个文件和行 |\n| 快速导览步骤过多 | 果断精简 |\n| 第一步是纯内容 | 将第一步锚定到真实文件或目录 |\n| 角色不匹配 | 为实际读者编写，而非通用工程师 |\n\n## 最佳实践\n\n* 步骤数量与仓库大小和角色深度成比例\n* 使用目录步骤进行定位，文件步骤用于实质内容\n* 对于 PR 导览，首先覆盖变更的文件\n* 对于单体仓库，将范围限定在相关包，而非导览所有内容\n* 以读者现在可以做什么来结束，而非总结\n\n## 相关技能\n\n* `codebase-onboarding`\n* `coding-standards`\n* `council`\n* 官方上游格式：`microsoft\u002Fcodetour`\n",{"name":5,"origin":24,"description":7},"ECC","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","web-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcode-tour",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill code-tour",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill code-tour",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill code-tour","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-CN\u002Fskills\u002Fcode-tour\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"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},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\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},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\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},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\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},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]