跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 foundation-models-on-device

Foundation Models On Device

苹果基金会 用于device LLM上的模型框架——文本生成,用@Genebable来引导生成,工具调用,以及快照流于iOS 26+. 在iOS 26+上与 Apple Foundation Models 添加上-device LLM 特性时使用.

8799 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

苹果基金会 iOS 26+中的device LLM的模型框架——文本生成,有指引的生成,使用@Genebable,工具调用和快照流

何时用

- 用于对隐私敏感的应用程序的在线设备文本生成

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:FoundationModels: On-Device LLM (iOS 26)、When to Activate、Core Pattern — Availability Check、Core Pattern — Basic Session、Core Pattern — Guided Generation with @Generable、1. Define a Generable Type。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. Use when adding on-device LLM features with Apple FoundationModels on iOS 26+.

FoundationModels: On-Device LLM (iOS 26)When to ActivateCore Pattern — Availability CheckCore Pattern — Basic SessionCore Pattern — Guided Generation with @Generable1. Define a Generable Type2. Request Structured OutputSupported @Guide ConstraintsCore Pattern — Tool Calling1. Define a Tool2. Create Session with Tools3. Handle Tool Errors

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
foundation-models-on-device
description
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. Use when adding on-device LLM features with Apple FoundationModels on iOS 26+.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「foundation-models-on-device」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-b8c4b66e3e3b9648-%E8%AE%BE%E5%A4%87%E4%B8%8A%E7%9A%84%E5%9F%BA%E7%A1%80%E6%A8%A1%E5%9E%8B.html
请存为 .cursor/skills/foundation-models-on-device/SKILL.md 或 .claude/skills/foundation-models-on-device/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/affaan-m/ecc' --list

npx skills add 'https://github.com/affaan-m/ecc' --skill 'foundation-models-on-device'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: foundation-models-on-device description: Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. Use when adding on-device LLM features with Apple FoundationModels on iOS 26+.

FoundationModels: On-Device LLM (iOS 26)

Patterns for integrating Apple's on-device language model into apps using the FoundationModels framework. Covers text generation, structured output with @Generable, custom tool calling, and snapshot streaming — all running on-device for privacy and offline support.

When to Activate

  • Building AI-powered features using Apple Intelligence on-device
  • Generating or summarizing text without cloud dependency
  • Extracting structured data from natural language input
  • Implementing custom tool calling for domain-specific AI actions
  • Streaming structured responses for real-time UI updates
  • Need privacy-preserving AI (no data leaves the device)

Core Pattern — Availability Check

Always check model availability before creating a session:

struct GenerativeView: View {
    private var model = SystemLanguageModel.default

    var body: some View {
        switch model.availability {
        case .available:
            ContentView()
        case .unavailable(.deviceNotEligible):
            Text("Device not eligible for Apple Intelligence")
        case .unavailable(.appleIntelligenceNotEnabled):
            Text("Please enable Apple Intelligence in Settings")
        case .unavailable(.modelNotReady):
            Text("Model is downloading or not ready")
        case .unavailable(let other):
            Text("Model unavailable: \(other)")
        }
    }
}

Core Pattern — Basic Session

// Single-turn: create a new session each time
let session = LanguageModelSession()
let response = try await session.respond(to: "What's a good month to visit Paris?")
print(response.content)

// Multi-turn: reuse session for conversation context
let session = LanguageModelSession(instructions: """
    You are a cooking assistant.
    Provide recipe suggestions based on ingredients.
    Keep suggestions brief and practical.
    """)

let first = try await session.respond(to: "I have chicken and rice")
let followUp = try await session.respond(to: "What about a vegetarian option?")

Key points for instructions:

  • Define the model's role ("You are a mentor")
  • Specify what to do ("Help extract calendar events")
  • Set style preferences ("Respond as briefly as possible")
  • Add safety measures ("Respond with 'I can't help with that' for dangerous requests")

Core Pattern — Guided Generation with @Generable

Generate structured Swift types instead of raw strings:

1. Define a Generable Type

@Generable(description: "Basic profile information about a cat")
struct CatProfile {
    var name: String

    @Guide(description: "The age of the cat", .range(0...20))
    var age: Int

    @Guide(description: "A one sentence profile about the cat's personality")
    var profile: String
}

2. Request Structured Output

let response = try await session.respond(
    to: "Generate a cute rescue cat",
    generating: CatProfile.self
)

// Access structured fields directly
print("Name: \(response.content.name)")
print("Age: \(response.content.age)")
print("Profile: \(response.content.profile)")

Supported @Guide Constraints

  • .range(0...20) — numeric range
  • .count(3) — array element count
  • description: — semantic guidance for generation

Core Pattern — Tool Calling

Let the model invoke custom code for domain-specific tasks:

1. Define a Tool

struct RecipeSearchTool: Tool {
    let name = "recipe_search"
    let description = "Search for recipes matching a given term and return a list of results."

    @Generable
    struct Arguments {
        var searchTerm: String
        var numberOfResults: Int
    }

    func call(arguments: Arguments) async throws -> ToolOutput {
        let recipes = await searchRecipes(
            term: arguments.searchTerm,
            limit: arguments.numberOfResults
        )
        return .string(recipes.map { "- \($0.name): \($0.description)" }.joined(separator: "\n"))
    }
}

2. Create Session with Tools

let session = LanguageModelSession(tools: [RecipeSearchTool()])
let response = try await session.respond(to: "Find me some pasta recipes")

3. Handle Tool Errors

do {
    let answer = try await session.respond(to: "Find a recipe for tomato soup.")
} catch let error as LanguageModelSession.ToolCallError {
    print(error.tool.name)
    if case .databaseIsEmpty = error.underlyingError as? RecipeSearchToolError {
        // Handle specific tool error
    }
}

Core Pattern — Snapshot Streaming

Stream structured responses for real-time UI with PartiallyGenerated types:

@Generable
struct TripIdeas {
    @Guide(description: "Ideas for upcoming trips")
    var ideas: [String]
}

let stream = session.streamResponse(
    to: "What are some exciting trip ideas?",
    generating: TripIdeas.self
)

for try await partial in stream {
    // partial: TripIdeas.PartiallyGenerated (all properties Optional)
    print(partial)
}

SwiftUI Integration

@State private var partialResult: TripIdeas.PartiallyGenerated?
@State private var errorMessage: String?

var body: some View {
    List {
        ForEach(partialResult?.ideas ?? [], id: \.self) { idea in
            Text(idea)
        }
    }
    .overlay {
        if let errorMessage { Text(errorMessage).foregroundStyle(.red) }
    }
    .task {
        do {
            let stream = session.streamResponse(to: prompt, generating: TripIdeas.self)
            for try await partial in stream {
                partialResult = partial
            }
        } catch {
            errorMessage = error.localizedDescription
        }
    }
}

Key Design Decisions

| Decision | Rationale | |----------|-----------| | On-device execution | Privacy — no data leaves the device; works offline | | 4,096 token limit | On-device model constraint; chunk large data across sessions | | Snapshot streaming (not deltas) | Structured output friendly; each snapshot is a complete partial state | | @Generable macro | Compile-time safety for structured generation; auto-generates PartiallyGenerated type | | Single request per session | isResponding prevents concurrent requests; create multiple sessions if needed | | response.content (not .output) | Correct API — always access results via .content property |

Best Practices

  • Always check model.availability before creating a session — handle all unavailability cases
  • Use instructions to guide model behavior — they take priority over prompts
  • Check isResponding before sending a new request — sessions handle one request at a time
  • Access response.content for results — not .output
  • Break large inputs into chunks — 4,096 token limit applies to instructions + prompt + output combined
  • Use @Generable for structured output — stronger guarantees than parsing raw strings
  • Use GenerationOptions(temperature:) to tune creativity (higher = more creative)
  • Monitor with Instruments — use Xcode Instruments to profile request performance

Anti-Patterns to Avoid

  • Creating sessions without checking model.availability first
  • Sending inputs exceeding the 4,096 token context window
  • Attempting concurrent requests on a single session
  • Using .output instead of .content to access response data
  • Parsing raw string responses when @Generable structured output would work
  • Building complex multi-step logic in a single prompt — break into multiple focused prompts
  • Assuming the model is always available — device eligibility and settings vary

When to Use

  • On-device text generation for privacy-sensitive apps
  • Structured data extraction from user input (forms, natural language commands)
  • AI-assisted features that must work offline
  • Streaming UI that progressively shows generated content
  • Domain-specific AI actions via tool calling (search, compute, lookup)

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…