Back to Details

axiom-ios-ai

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

iOS Apple Intelligence Router

iOS Apple Intelligence 路由

You MUST use this skill for ANY Apple Intelligence or Foundation Models work.
任何Apple Intelligence或Foundation Models相关工作都必须使用此技能。

When to Use

适用场景

Use this router when:
  • Implementing Apple Intelligence features
  • Using Foundation Models
  • Working with LanguageModelSession
  • Generating structured output with @Generable
  • Debugging AI generation issues
  • iOS 26 on-device AI
在以下场景使用此路由：
  • 实现Apple Intelligence功能
  • 使用Foundation Models
  • 开发LanguageModelSession相关功能
  • 利用@Generable生成结构化输出
  • 调试AI生成相关问题
  • iOS 26设备端AI开发

Routing Logic

路由逻辑

Foundation Models Work

Foundation Models 开发

Implementation patterns → 
/skill axiom-foundation-models
  • LanguageModelSession basics
  • @Generable structured output
  • Tool protocol integration
  • Streaming with PartiallyGenerated
  • Dynamic schemas
  • 26 WWDC code examples
API reference → 
/skill axiom-foundation-models-ref
  • Complete API documentation
  • All @Generable examples
  • Tool protocol patterns
  • Streaming generation patterns
Diagnostics → 
/skill axiom-foundation-models-diag
  • AI response blocked
  • Generation slow
  • Guardrail violations
  • Context limits exceeded
  • Model unavailable
实现模式 → 
/skill axiom-foundation-models
  • LanguageModelSession基础用法
  • @Generable结构化输出
  • Tool协议集成
  • 基于PartiallyGenerated的流式处理
  • 动态模式
  • 26届WWDC代码示例
API参考 → 
/skill axiom-foundation-models-ref
  • 完整API文档
  • 所有@Generable示例
  • Tool协议模式
  • 流式生成模式
诊断调试 → 
/skill axiom-foundation-models-diag
  • AI响应被拦截
  • 生成速度缓慢
  • 违反安全规则
  • 超出上下文限制
  • 模型不可用

Decision Tree

决策树

  1. Implementing Foundation Models / @Generable / Tool protocol? → foundation-models
  2. Need API reference / code examples? → foundation-models-ref
  3. Debugging AI issues (blocked, slow, guardrails)? → foundation-models-diag
  1. 是否在实现Foundation Models / @Generable / Tool协议相关功能？ → foundation-models
  2. 是否需要API参考/代码示例？ → foundation-models-ref
  3. 是否在调试AI问题（拦截、缓慢、安全规则）？ → foundation-models-diag

Anti-Rationalization

常见误区澄清

ThoughtReality
"Foundation Models is just LanguageModelSession"Foundation Models has @Generable, Tool protocol, streaming, and guardrails. foundation-models covers all.
"I'll figure out the AI patterns as I go"AI APIs have specific error handling and fallback requirements. foundation-models prevents runtime failures.
"I've used LLMs before, this is similar"Apple's on-device models have unique constraints (guardrails, context limits). foundation-models is Apple-specific.
错误想法实际情况
"Foundation Models 只是LanguageModelSession"Foundation Models包含@Generable、Tool协议、流式处理和安全规则，foundation-models技能覆盖所有这些内容。
"我可以边开发边摸索AI模式"AI API有特定的错误处理和回退要求，foundation-models技能可避免运行时故障。
"我之前用过LLM，这个应该类似"Apple的设备端模型有独特约束（安全规则、上下文限制），foundation-models是Apple专属的技能。

Critical Patterns

核心模式

foundation-models:
  • LanguageModelSession setup
  • @Generable for structured output
  • Tool protocol for function calling
  • Streaming generation
  • Dynamic schema evolution
foundation-models-diag:
  • Blocked response handling
  • Performance optimization
  • Guardrail violations
  • Context management
foundation-models:
  • LanguageModelSession配置
  • 利用@Generable实现结构化输出
  • 基于Tool协议的函数调用
  • 流式生成
  • 动态模式演进
foundation-models-diag:
  • 拦截响应处理
  • 性能优化
  • 安全规则违规处理
  • 上下文管理

Example Invocations

调用示例

User: "How do I use Apple Intelligence to generate structured data?" → Invoke: 
/skill axiom-foundation-models
User: "My AI generation is being blocked" → Invoke: 
/skill axiom-foundation-models-diag
User: "Show me @Generable examples" → Invoke: 
/skill axiom-foundation-models-ref
User: "Implement streaming AI generation" → Invoke: 
/skill axiom-foundation-models
用户："如何使用Apple Intelligence生成结构化数据？" → 调用：
/skill axiom-foundation-models
用户："我的AI生成被拦截了" → 调用：
/skill axiom-foundation-models-diag
用户："展示@Generable的示例" → 调用：
/skill axiom-foundation-models-ref
用户："实现流式AI生成" → 调用：
/skill axiom-foundation-models