Best fit
- 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。
affaan-m/ECC
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。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/foundation-models-on-device"Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
According to the pinned SKILL.md from affaan-m/ECC: 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。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/foundation-models-on-device"Best fit
Bring this context
Expected outputs
Key source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
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)
Review the “核心模式 — 可用性检查” section in the pinned source before continuing.
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'")
生成结构化的 Swift 类型,而不是原始字符串:
Review the “1. 定义可生成类型” section in the pinned source before continuing.
SkillSignal prompt templates
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use foundation-models-on-device to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned foundation-models-on-device source to [task]. Pay particular attention to these source sections: “何时启用”, “核心模式 — 可用性检查”, “核心模式 — 基础会话”, “核心模式 — 使用 @Generable 进行引导式生成”, “1. 定义可生成类型”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current foundation-models-on-device result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
The task matches the purpose documented in the SKILL.md.
The source section “何时启用” has been checked.
The source section “核心模式 — 可用性检查” has been checked.
The source section “核心模式 — 基础会话” has been checked.
The source section “核心模式 — 使用 @Generable 进行引导式生成” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailWhen the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
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。
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/foundation-models-on-device". Inspect the command and pinned source before running it.
No dedicated Agent platform is declared in the pinned source record.
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Compare before choosing
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
Write and maintain DESIGN.md + PRODUCT.md — captures visual decisions and interaction patterns so design tasks stay consistent across sessions without re-scanning past work.
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。
在创建会话之前,始终检查模型可用性:
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)")
}
}
}
// 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:
生成结构化的 Swift 类型,而不是原始字符串:
@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
}
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)")
.range(0...20) — 数值范围.count(3) — 数组元素数量description: — 生成的语义引导让模型调用自定义代码以执行特定领域的任务:
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"))
}
}
let session = LanguageModelSession(tools: [RecipeSearchTool()])
let response = try await session.respond(to: "Find me some pasta recipes")
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
}
}
使用 PartiallyGenerated 类型为实时 UI 流式传输结构化响应:
@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)
}
@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
}
}
}
| 决策 | 理由 |
|---|---|
| 设备端执行 | 隐私性——数据不离开设备;支持离线工作 |
| 4,096 个令牌限制 | 设备端模型约束;跨会话分块处理大数据 |
| 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 |
@Generable 宏 | 为结构化生成提供编译时安全性;自动生成 PartiallyGenerated 类型 |
| 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 |
response.content(而非 .output) | 正确的 API——始终通过 .content 属性访问结果 |
model.availability——处理所有不可用的情况instructions 来引导模型行为——它们的优先级高于提示词isResponding——会话一次处理一个请求response.content 访问结果——而不是 .output@Generable——比解析原始字符串提供更强的保证GenerationOptions(temperature:) 来调整创造力(值越高越有创意)model.availability 就创建会话.output 而不是 .content 来访问响应数据@Generable 结构化输出可行时,却去解析原始字符串响应