[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6E1J04DXTWWRAMKKABWVB9M":3,"skill-same:01M6E1J04DXTWWRAMKKABWVB9M":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":13,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6E1J04DXTWWRAMKKABWVB9M","foundation-models-on-device",null,"苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。","7dvq6yrkgs-stack\u002Fplaywright","7dvq6yrkgs-stack","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F251638143?v=4","01M6E061J2AMGWYZ6TK7Y8NM74","01M6E061PQCQJGQMPBERMCFN5G",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-models-on-device\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[23,24,25,26,27,28],"models","foundation","device","foundation models on device","生成","文本","2026-11-10 10:12:30",false,"---\nname: foundation-models-on-device\ndescription: 苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。\n---\n\n# FoundationModels：设备端 LLM（iOS 26）\n\n使用 FoundationModels 框架将苹果的设备端语言模型集成到应用中的模式。涵盖文本生成、使用 `@Generable` 的结构化输出、自定义工具调用以及快照流式传输——全部在设备端运行，以保护隐私并支持离线使用。\n\n## 何时启用\n\n* 使用 Apple Intelligence 在设备端构建 AI 功能\n* 无需依赖云端即可生成或总结文本\n* 从自然语言输入中提取结构化数据\n* 为特定领域的 AI 操作实现自定义工具调用\n* 流式传输结构化响应以实现实时 UI 更新\n* 需要保护隐私的 AI（数据不离开设备）\n\n## 核心模式 — 可用性检查\n\n在创建会话之前，始终检查模型可用性：\n\n```swift\nstruct GenerativeView: View {\n    private var model = SystemLanguageModel.default\n\n    var body: some View {\n        switch model.availability {\n        case .available:\n            ContentView()\n        case .unavailable(.deviceNotEligible):\n            Text(\"Device not eligible for Apple Intelligence\")\n        case .unavailable(.appleIntelligenceNotEnabled):\n            Text(\"Please enable Apple Intelligence in Settings\")\n        case .unavailable(.modelNotReady):\n            Text(\"Model is downloading or not ready\")\n        case .unavailable(let other):\n            Text(\"Model unavailable: \\(other)\")\n        }\n    }\n}\n```\n\n## 核心模式 — 基础会话\n\n```swift\n\u002F\u002F Single-turn: create a new session each time\nlet session = LanguageModelSession()\nlet response = try await session.respond(to: \"What's a good month to visit Paris?\")\nprint(response.content)\n\n\u002F\u002F Multi-turn: reuse session for conversation context\nlet session = LanguageModelSession(instructions: \"\"\"\n    You are a cooking assistant.\n    Provide recipe suggestions based on ingredients.\n    Keep suggestions brief and practical.\n    \"\"\")\n\nlet first = try await session.respond(to: \"I have chicken and rice\")\nlet followUp = try await session.respond(to: \"What about a vegetarian option?\")\n```\n\n指令的关键点：\n\n* 定义模型的角色（\"你是一位导师\"）\n* 指定要做什么（\"帮助提取日历事件\"）\n* 设置风格偏好（\"尽可能简短地回答\"）\n* 添加安全措施（\"对于危险请求，回复'我无法提供帮助'\"）\n\n## 核心模式 — 使用 @Generable 进行引导式生成\n\n生成结构化的 Swift 类型，而不是原始字符串：\n\n### 1. 定义可生成类型\n\n```swift\n@Generable(description: \"Basic profile information about a cat\")\nstruct CatProfile {\n    var name: String\n\n    @Guide(description: \"The age of the cat\", .range(0...20))\n    var age: Int\n\n    @Guide(description: \"A one sentence profile about the cat's personality\")\n    var profile: String\n}\n```\n\n### 2. 请求结构化输出\n\n```swift\nlet response = try await session.respond(\n    to: \"Generate a cute rescue cat\",\n    generating: CatProfile.self\n)\n\n\u002F\u002F Access structured fields directly\nprint(\"Name: \\(response.content.name)\")\nprint(\"Age: \\(response.content.age)\")\nprint(\"Profile: \\(response.content.profile)\")\n```\n\n### 支持的 @Guide 约束\n\n* `.range(0...20)` — 数值范围\n* `.count(3)` — 数组元素数量\n* `description:` — 生成的语义引导\n\n## 核心模式 — 工具调用\n\n让模型调用自定义代码以执行特定领域的任务：\n\n### 1. 定义工具\n\n```swift\nstruct RecipeSearchTool: Tool {\n    let name = \"recipe_search\"\n    let description = \"Search for recipes matching a given term and return a list of results.\"\n\n    @Generable\n    struct Arguments {\n        var searchTerm: String\n        var numberOfResults: Int\n    }\n\n    func call(arguments: Arguments) async throws -> ToolOutput {\n        let recipes = await searchRecipes(\n            term: arguments.searchTerm,\n            limit: arguments.numberOfResults\n        )\n        return .string(recipes.map { \"- \\($0.name): \\($0.description)\" }.joined(separator: \"\\n\"))\n    }\n}\n```\n\n### 2. 创建带工具的会话\n\n```swift\nlet session = LanguageModelSession(tools: [RecipeSearchTool()])\nlet response = try await session.respond(to: \"Find me some pasta recipes\")\n```\n\n### 3. 处理工具错误\n\n```swift\ndo {\n    let answer = try await session.respond(to: \"Find a recipe for tomato soup.\")\n} catch let error as LanguageModelSession.ToolCallError {\n    print(error.tool.name)\n    if case .databaseIsEmpty = error.underlyingError as? RecipeSearchToolError {\n        \u002F\u002F Handle specific tool error\n    }\n}\n```\n\n## 核心模式 — 快照流式传输\n\n使用 `PartiallyGenerated` 类型为实时 UI 流式传输结构化响应：\n\n```swift\n@Generable\nstruct TripIdeas {\n    @Guide(description: \"Ideas for upcoming trips\")\n    var ideas: [String]\n}\n\nlet stream = session.streamResponse(\n    to: \"What are some exciting trip ideas?\",\n    generating: TripIdeas.self\n)\n\nfor try await partial in stream {\n    \u002F\u002F partial: TripIdeas.PartiallyGenerated (all properties Optional)\n    print(partial)\n}\n```\n\n### SwiftUI 集成\n\n```swift\n@State private var partialResult: TripIdeas.PartiallyGenerated?\n@State private var errorMessage: String?\n\nvar body: some View {\n    List {\n        ForEach(partialResult?.ideas ?? [], id: \\.self) { idea in\n            Text(idea)\n        }\n    }\n    .overlay {\n        if let errorMessage { Text(errorMessage).foregroundStyle(.red) }\n    }\n    .task {\n        do {\n            let stream = session.streamResponse(to: prompt, generating: TripIdeas.self)\n            for try await partial in stream {\n                partialResult = partial\n            }\n        } catch {\n            errorMessage = error.localizedDescription\n        }\n    }\n}\n```\n\n## 关键设计决策\n\n| 决策 | 理由 |\n|----------|-----------|\n| 设备端执行 | 隐私性——数据不离开设备；支持离线工作 |\n| 4,096 个令牌限制 | 设备端模型约束；跨会话分块处理大数据 |\n| 快照流式传输（非增量） | 对结构化输出友好；每个快照都是一个完整的部分状态 |\n| `@Generable` 宏 | 为结构化生成提供编译时安全性；自动生成 `PartiallyGenerated` 类型 |\n| 每个会话单次请求 | `isResponding` 防止并发请求；如有需要，创建多个会话 |\n| `response.content`（而非 `.output`） | 正确的 API——始终通过 `.content` 属性访问结果 |\n\n## 最佳实践\n\n* 在创建会话之前**始终检查 `model.availability`**——处理所有不可用的情况\n* **使用 `instructions`** 来引导模型行为——它们的优先级高于提示词\n* 在发送新请求之前**检查 `isResponding`**——会话一次处理一个请求\n* 通过 `response.content` **访问结果**——而不是 `.output`\n* **将大型输入分块处理**——4,096 个令牌的限制适用于指令、提示词和输出的总和\n* 对于结构化输出**使用 `@Generable`**——比解析原始字符串提供更强的保证\n* **使用 `GenerationOptions(temperature:)`** 来调整创造力（值越高越有创意）\n* **使用 Instruments 进行监控**——使用 Xcode Instruments 来分析请求性能\n\n## 应避免的反模式\n\n* 未先检查 `model.availability` 就创建会话\n* 发送超过 4,096 个令牌上下文窗口的输入\n* 尝试在单个会话上进行并发请求\n* 使用 `.output` 而不是 `.content` 来访问响应数据\n* 当 `@Generable` 结构化输出可行时，却去解析原始字符串响应\n* 在单个提示词中构建复杂的多步逻辑——将其拆分为多个聚焦的提示词\n* 假设模型始终可用——设备的资格和设置各不相同\n\n## 何时使用\n\n* 为注重隐私的应用进行设备端文本生成\n* 从用户输入（表单、自然语言命令）中提取结构化数据\n* 必须离线工作的 AI 辅助功能\n* 逐步显示生成内容的流式 UI\n* 通过工具调用（搜索、计算、查找）执行特定领域的 AI 操作\n","# FoundationModels：设备端 LLM（iOS 26）\n\n使用 FoundationModels 框架将苹果的设备端语言模型集成到应用中的模式。涵盖文本生成、使用 `@Generable` 的结构化输出、自定义工具调用以及快照流式传输——全部在设备端运行，以保护隐私并支持离线使用。\n\n## 何时启用\n\n* 使用 Apple Intelligence 在设备端构建 AI 功能\n* 无需依赖云端即可生成或总结文本\n* 从自然语言输入中提取结构化数据\n* 为特定领域的 AI 操作实现自定义工具调用\n* 流式传输结构化响应以实现实时 UI 更新\n* 需要保护隐私的 AI（数据不离开设备）\n\n## 核心模式 — 可用性检查\n\n在创建会话之前，始终检查模型可用性：\n\n```swift\nstruct GenerativeView: View {\n    private var model = SystemLanguageModel.default\n\n    var body: some View {\n        switch model.availability {\n        case .available:\n            ContentView()\n        case .unavailable(.deviceNotEligible):\n            Text(\"Device not eligible for Apple Intelligence\")\n        case .unavailable(.appleIntelligenceNotEnabled):\n            Text(\"Please enable Apple Intelligence in Settings\")\n        case .unavailable(.modelNotReady):\n            Text(\"Model is downloading or not ready\")\n        case .unavailable(let other):\n            Text(\"Model unavailable: \\(other)\")\n        }\n    }\n}\n```\n\n## 核心模式 — 基础会话\n\n```swift\n\u002F\u002F Single-turn: create a new session each time\nlet session = LanguageModelSession()\nlet response = try await session.respond(to: \"What's a good month to visit Paris?\")\nprint(response.content)\n\n\u002F\u002F Multi-turn: reuse session for conversation context\nlet session = LanguageModelSession(instructions: \"\"\"\n    You are a cooking assistant.\n    Provide recipe suggestions based on ingredients.\n    Keep suggestions brief and practical.\n    \"\"\")\n\nlet first = try await session.respond(to: \"I have chicken and rice\")\nlet followUp = try await session.respond(to: \"What about a vegetarian option?\")\n```\n\n指令的关键点：\n\n* 定义模型的角色（\"你是一位导师\"）\n* 指定要做什么（\"帮助提取日历事件\"）\n* 设置风格偏好（\"尽可能简短地回答\"）\n* 添加安全措施（\"对于危险请求，回复'我无法提供帮助'\"）\n\n## 核心模式 — 使用 @Generable 进行引导式生成\n\n生成结构化的 Swift 类型，而不是原始字符串：\n\n### 1. 定义可生成类型\n\n```swift\n@Generable(description: \"Basic profile information about a cat\")\nstruct CatProfile {\n    var name: String\n\n    @Guide(description: \"The age of the cat\", .range(0...20))\n    var age: Int\n\n    @Guide(description: \"A one sentence profile about the cat's personality\")\n    var profile: String\n}\n```\n\n### 2. 请求结构化输出\n\n```swift\nlet response = try await session.respond(\n    to: \"Generate a cute rescue cat\",\n    generating: CatProfile.self\n)\n\n\u002F\u002F Access structured fields directly\nprint(\"Name: \\(response.content.name)\")\nprint(\"Age: \\(response.content.age)\")\nprint(\"Profile: \\(response.content.profile)\")\n```\n\n### 支持的 @Guide 约束\n\n* `.range(0...20)` — 数值范围\n* `.count(3)` — 数组元素数量\n* `description:` — 生成的语义引导\n\n## 核心模式 — 工具调用\n\n让模型调用自定义代码以执行特定领域的任务：\n\n### 1. 定义工具\n\n```swift\nstruct RecipeSearchTool: Tool {\n    let name = \"recipe_search\"\n    let description = \"Search for recipes matching a given term and return a list of results.\"\n\n    @Generable\n    struct Arguments {\n        var searchTerm: String\n        var numberOfResults: Int\n    }\n\n    func call(arguments: Arguments) async throws -> ToolOutput {\n        let recipes = await searchRecipes(\n            term: arguments.searchTerm,\n            limit: arguments.numberOfResults\n        )\n        return .string(recipes.map { \"- \\($0.name): \\($0.description)\" }.joined(separator: \"\\n\"))\n    }\n}\n```\n\n### 2. 创建带工具的会话\n\n```swift\nlet session = LanguageModelSession(tools: [RecipeSearchTool()])\nlet response = try await session.respond(to: \"Find me some pasta recipes\")\n```\n\n### 3. 处理工具错误\n\n```swift\ndo {\n    let answer = try await session.respond(to: \"Find a recipe for tomato soup.\")\n} catch let error as LanguageModelSession.ToolCallError {\n    print(error.tool.name)\n    if case .databaseIsEmpty = error.underlyingError as? RecipeSearchToolError {\n        \u002F\u002F Handle specific tool error\n    }\n}\n```\n\n## 核心模式 — 快照流式传输\n\n使用 `PartiallyGenerated` 类型为实时 UI 流式传输结构化响应：\n\n```swift\n@Generable\nstruct TripIdeas {\n    @Guide(description: \"Ideas for upcoming trips\")\n    var ideas: [String]\n}\n\nlet stream = session.streamResponse(\n    to: \"What are some exciting trip ideas?\",\n    generating: TripIdeas.self\n)\n\nfor try await partial in stream {\n    \u002F\u002F partial: TripIdeas.PartiallyGenerated (all properties Optional)\n    print(partial)\n}\n```\n\n### SwiftUI 集成\n\n```swift\n@State private var partialResult: TripIdeas.PartiallyGenerated?\n@State private var errorMessage: String?\n\nvar body: some View {\n    List {\n        ForEach(partialResult?.ideas ?? [], id: \\.self) { idea in\n            Text(idea)\n        }\n    }\n    .overlay {\n        if let errorMessage { Text(errorMessage).foregroundStyle(.red) }\n    }\n    .task {\n        do {\n            let stream = session.streamResponse(to: prompt, generating: TripIdeas.self)\n            for try await partial in stream {\n                partialResult = partial\n            }\n        } catch {\n            errorMessage = error.localizedDescription\n        }\n    }\n}\n```\n\n## 关键设计决策\n\n| 决策 | 理由 |\n|----------|-----------|\n| 设备端执行 | 隐私性——数据不离开设备；支持离线工作 |\n| 4,096 个令牌限制 | 设备端模型约束；跨会话分块处理大数据 |\n| 快照流式传输（非增量） | 对结构化输出友好；每个快照都是一个完整的部分状态 |\n| `@Generable` 宏 | 为结构化生成提供编译时安全性；自动生成 `PartiallyGenerated` 类型 |\n| 每个会话单次请求 | `isResponding` 防止并发请求；如有需要，创建多个会话 |\n| `response.content`（而非 `.output`） | 正确的 API——始终通过 `.content` 属性访问结果 |\n\n## 最佳实践\n\n* 在创建会话之前**始终检查 `model.availability`**——处理所有不可用的情况\n* **使用 `instructions`** 来引导模型行为——它们的优先级高于提示词\n* 在发送新请求之前**检查 `isResponding`**——会话一次处理一个请求\n* 通过 `response.content` **访问结果**——而不是 `.output`\n* **将大型输入分块处理**——4,096 个令牌的限制适用于指令、提示词和输出的总和\n* 对于结构化输出**使用 `@Generable`**——比解析原始字符串提供更强的保证\n* **使用 `GenerationOptions(temperature:)`** 来调整创造力（值越高越有创意）\n* **使用 Instruments 进行监控**——使用 Xcode Instruments 来分析请求性能\n\n## 应避免的反模式\n\n* 未先检查 `model.availability` 就创建会话\n* 发送超过 4,096 个令牌上下文窗口的输入\n* 尝试在单个会话上进行并发请求\n* 使用 `.output` 而不是 `.content` 来访问响应数据\n* 当 `@Generable` 结构化输出可行时，却去解析原始字符串响应\n* 在单个提示词中构建复杂的多步逻辑——将其拆分为多个聚焦的提示词\n* 假设模型始终可用——设备的资格和设置各不相同\n\n## 何时使用\n\n* 为注重隐私的应用进行设备端文本生成\n* 从用户输入（表单、自然语言命令）中提取结构化数据\n* 必须离线工作的 AI 辅助功能\n* 逐步显示生成内容的流式 UI\n* 通过工具调用（搜索、计算、查找）执行特定领域的 AI 操作\n",{"name":5,"description":7},"main","a2e3284ed4488780397ee2f78217366e11470dfb","skills\u002Ffoundation-models-on-device","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright","https:\u002F\u002Fplaywright.dev","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack","2026-04-25 06:04:45",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add 7dvq6yrkgs-stack\u002Fplaywright --skill foundation-models-on-device",{"tool":47,"command":48},"bunx","bunx skills add 7dvq6yrkgs-stack\u002Fplaywright --skill foundation-models-on-device",{"tool":50,"command":51},"pnpm","pnpm dlx skills add 7dvq6yrkgs-stack\u002Fplaywright --skill foundation-models-on-device","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-models-on-device\u002FSKILL.md",true,[55,61,65,69,73,77,81],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},".skillfish.json","REFERENCE","参考文档",272,"https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-models-on-device\u002F.skillfish.json",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fdpo-variants.md",4297,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Freferences\u002Fdpo-variants.md",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fgrpo-training.md",15901,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Freferences\u002Fgrpo-training.md",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fonline-rl.md",1971,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Freferences\u002Fonline-rl.md",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Freward-modeling.md",2597,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Freferences\u002Freward-modeling.md",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsft-training.md",3237,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Freferences\u002Fsft-training.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"templates\u002Fbasic_grpo_training.py","SCRIPT","脚本",6113,"https:\u002F\u002Fgithub.com\u002F0xzgbot\u002Fforge-nps-v01\u002Fblob\u002Fmaster\u002Fhermes_home\u002Fprofiles\u002Fcinesmith\u002Fskills\u002Fmlops\u002Ftraining\u002Ftrl-fine-tuning\u002Ftemplates\u002Fbasic_grpo_training.py",[88,118,128,138,153,168],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":106,"publishedAt":29},"01M6E3XK4PRPMQHM7Y98FQPTY1","zyte-api-automation","Automate Zyte API tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzyte-api-automation\u002FSKILL.md",[94,95,98,101],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":96,"categoryName":97,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[107,108,109,110,111,112,113,114,115,116,117],"zyte api automation","api","automation","MCP","tasks","search","Tools","first","automate","composio","via",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":126,"publishedAt":29},"01M6E3XFX6QSTR1QR59NFXJTMA","zylvie-automation","Automate Zylvie tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzylvie-automation\u002FSKILL.md",[124,125],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},[127,109,115,110,111,112,113,114,116,117],"zylvie automation",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":136,"publishedAt":29},"01M6E3XCX2GDYYCHN58ZJHT37M","zoominfo-automation","Automate Zoominfo tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzoominfo-automation\u002FSKILL.md",[134,135],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},[137,109,112,113,114,115,116,117,111,110],"zoominfo automation",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":146,"publishedAt":29},"01M6E3X9WJ2T73216WQHHTB9BD","zoho_mail-automation","Automate Zoho Mail tasks via Rube MCP (Composio): email sending, folders, labels, and mailbox management. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzoho_mail-automation\u002FSKILL.md",[144,145],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},[147,148,149,109,110,111,112,150,113,114,115,151,116,152,117],"mail","zoho mail automation","zoho","email","management","mailbox",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":164,"publishedAt":29},"01M6E3X719W648XZBW1EC6JQ64","zoho_invoice-automation","Automate Zoho Invoice tasks via Rube MCP (Composio): invoices, estimates, expenses, clients, and payment tracking. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzoho_invoice-automation\u002FSKILL.md",[159,160,161],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":162,"categoryName":163,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000040","财务",[165,149,109,111,112,113,114,115,166,167,116,117,110],"zoho invoice automation","tracking","payment",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":176,"publishedAt":29},"01M6E3X28JYTC3QTK32AQF7BYB","zoho_inventory-automation","Automate Zoho Inventory tasks via Rube MCP (Composio): items, orders, warehouses, shipments, and stock management. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002F7dvq6yrkgs-stack\u002Fplaywright\u002Fblob\u002Fmain\u002Fskills\u002Fzoho_inventory-automation\u002FSKILL.md",[174,175],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},[109,177,149,178,114,115,113,112,111,110,116,117,179,180,151],"inventory","zoho inventory automation","stock","orders"]