All skills

foundation-models-on-device

Official
by Api.AirforcePrepends a system promptAI & Agent Building000 uses202,700

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。

open-sourceclaude-codeai-agent-buildingaffaan-m
Share

What this skill does

When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.

---
name: foundation-models-on-device
description: 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。
---

# FoundationModels:设备端 LLM(iOS 26)

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。

## 何时启用

* 使用 Apple Intelligence 在设备端构建 AI 功能
* 无需依赖云端即可生成或总结文本
* 从自然语言输入中提取结构化数据
* 为特定领域的 AI 操作实现自定义工具调用
* 流式传输结构化响应以实现实时 UI 更新
* 需要保护隐私的 AI(数据不离开设备)

## 核心模式 — 可用性检查

在创建会话之前,始终检查模型可用性:

```swift
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)")
        }
    }
}
```

## 核心模式 — 基础会话

```swift
// 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?")
```

指令的关键点:

* 定义模型的角色("你是一位导师")
* 指定要做什么("帮助提取日历事件")
* 设置风格偏好("尽可能简短地回答")
* 添加安全措施("对于危险请求,回复'我无法提供帮助'")

## 核心模式 — 使用 @Generable 进行引导式生成

生成结构化的 Swift 类型,而不是原始字符串:

### 1. 定义可生成类型

```swift
@Generable(description: "Basic profile information about a cat")
struct CatProfi

Use this skill

Per request

Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.

{
  "model": "gpt-4o-mini",
  "skill": "imp-05e5e33e-18f7-42e3-937a-9e0cfbd637e6",
  "messages": [{ "role": "user", "content": "…" }]
}
Always on — no field to send

Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.

Set it up in your dashboard