axiom-ai

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Apple Intelligence & AI

Apple Intelligence与AI

You MUST use this skill for ANY Apple Intelligence or Foundation Models work.

任何涉及Apple Intelligence或Foundation Models的工作都必须使用此技能。

When to Use

使用场景

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

在以下场景中使用此路由：

实现Apple Intelligence功能
使用Foundation Models
开发LanguageModelSession相关功能
通过@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

AI Approach Triage

AI方法分流

First, determine which kind of AI the developer needs:

Developer Intent	Route To
On-device text generation (Apple Intelligence)	Stay here → Foundation Models skills
Custom ML model deployment (PyTorch, TensorFlow)	See skills/ios-ml.md → CoreML conversion, compression
Computer vision (image analysis, OCR, segmentation)	/skill axiom-vision → Vision framework
Cloud API integration (OpenAI, etc.)	/skill axiom-networking → URLSession patterns
System AI features (Writing Tools, Genmoji)	No custom code needed — these are system-provided

Key boundary: Foundation Models vs ML (custom models)

Foundation Models = Apple's on-device LLM framework (LanguageModelSession, @Generable)
ML = Custom model deployment (CoreML conversion, quantization, MLTensor, speech-to-text)
If developer says "run my own model" → skills/ios-ml.md. If "use Apple Intelligence" → stay here.

首先，确定开发者需要的AI类型：

开发者需求	路由至
设备端文本生成（Apple Intelligence）	留在此处 → Foundation Models技能
自定义ML模型部署（PyTorch、TensorFlow）	查看skills/ios-ml.md → CoreML转换、压缩
计算机视觉（图像分析、OCR、分割）	/skill axiom-vision → Vision框架
云API集成（OpenAI等）	/skill axiom-networking → URLSession模式
系统AI功能（写作工具、Genmoji）	无需自定义代码——这些是系统自带功能

关键边界：Foundation Models vs ML（自定义模型）

Foundation Models = 苹果的设备端LLM框架（LanguageModelSession、@Generable）
ML = 自定义模型部署（CoreML转换、量化、MLTensor、语音转文本）
如果开发者提到“运行我自己的模型” → 查看skills/ios-ml.md。如果是“使用Apple Intelligence” → 留在此处。

Cross-Domain Routing

跨域路由

Foundation Models + concurrency (session blocking main thread, UI freezes):

Foundation Models sessions are async — blocking likely means missing
```
await
```
or running on @MainActor
Fix here first using async session patterns in foundation-models skill
If concurrency issue is broader than Foundation Models → also invoke axiom-concurrency

Foundation Models + data (@Generable decoding errors, structured output issues):

@Generable output problems are Foundation Models-specific, NOT generic Codable issues
Stay here → foundation-models-diag handles structured output debugging
If developer also has general Codable/serialization questions → also invoke axiom-data

Foundation Models + 并发（会话阻塞主线程、UI冻结）：

Foundation Models会话是异步的——阻塞可能意味着缺少
```
await
```
或在@MainActor上运行
首先在此修复，使用foundation-models技能中的异步会话模式
如果并发问题超出Foundation Models范畴 → 同时调用axiom-concurrency

Foundation Models + 数据（@Generable解码错误、结构化输出问题）：

@Generable输出问题是Foundation Models特有的，而非通用Codable问题
留在此处 → foundation-models-diag处理结构化输出调试
如果开发者同时有通用Codable/序列化问题 → 同时调用axiom-data

Routing Logic

路由逻辑

Foundation Models Work

Foundation Models开发

Implementation patterns →

skills/foundation-models.md

LanguageModelSession basics
@Generable structured output
Tool protocol integration
Streaming with PartiallyGenerated
Dynamic schemas
26 WWDC code examples

API reference →

skills/foundation-models-ref.md

Complete API documentation
All @Generable examples
Tool protocol patterns
Streaming generation patterns

Diagnostics →

skills/foundation-models-diag.md

AI response blocked
Generation slow
Guardrail violations
Context limits exceeded
Model unavailable

Automated scanning → Launch

foundation-models-auditor

agent or

/axiom:audit foundation-models

(missing availability checks, main thread blocking, manual JSON parsing, session lifecycle issues)

实现模式 →

skills/foundation-models.md

LanguageModelSession基础
@Generable结构化输出
Tool协议集成
使用PartiallyGenerated进行流式处理
动态 schema
26届WWDC代码示例

API参考 →

skills/foundation-models-ref.md

完整API文档
所有@Generable示例
Tool协议模式
流式生成模式

诊断 →

skills/foundation-models-diag.md

AI响应被拦截
生成速度慢
违反防护规则
超出上下文限制
模型不可用

自动化扫描 → 启动

foundation-models-auditor

代理或执行

/axiom:audit foundation-models

（检查缺失的可用性检测、主线程阻塞、手动JSON解析、会话生命周期问题）

Decision Tree

决策树

Custom ML model / CoreML / PyTorch conversion? → See skills/ios-ml.md
Computer vision / image analysis / OCR? → /skill axiom-vision
Cloud AI API integration? → /skill axiom-networking
Implementing Foundation Models / @Generable / Tool protocol? → foundation-models
Need API reference / code examples? → foundation-models-ref
Debugging AI issues (blocked, slow, guardrails)? → foundation-models-diag
Foundation Models + UI freezing? → foundation-models (async patterns) + also invoke axiom-concurrency if needed
Want automated Foundation Models code scan? → foundation-models-auditor (Agent)

自定义ML模型/CoreML/PyTorch转换？ → 查看skills/ios-ml.md
计算机视觉/图像分析/OCR？ → /skill axiom-vision
云AI API集成？ → /skill axiom-networking
实现Foundation Models/@Generable/Tool协议？ → foundation-models
需要API参考/代码示例？ → foundation-models-ref
调试AI问题（拦截、缓慢、防护规则）？ → foundation-models-diag
Foundation Models + UI冻结？ → foundation-models（异步模式）+ 必要时同时调用axiom-concurrency
想要自动化Foundation Models代码扫描？ → foundation-models-auditor（Agent）

Anti-Rationalization

误区纠正

Thought	Reality
"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、流式处理和防护规则。foundation-models技能涵盖所有这些内容。
"我会边做边摸索AI模式"	AI API有特定的错误处理和回退要求。foundation-models技能可防止运行时故障。
"我之前用过LLM，这个类似"	苹果的设备端模型有独特的限制（防护规则、上下文限制）。foundation-models是苹果专属的技能。

Critical Patterns

关键模式

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设置
使用@Generable实现结构化输出
Tool协议用于函数调用
流式生成
动态schema演进

foundation-models-diag：

拦截响应处理
性能优化
防护规则违规处理
上下文管理

Example Invocations

调用示例

User: "How do I use Apple Intelligence to generate structured data?" → Read:

skills/foundation-models.md

User: "My AI generation is being blocked" → Read:

skills/foundation-models-diag.md

User: "Show me @Generable examples" → Read:

skills/foundation-models-ref.md

User: "Implement streaming AI generation" → Read:

skills/foundation-models.md

User: "I want to add AI to my app" → First ask: Apple Intelligence (Foundation Models) or custom ML model? Route accordingly.

User: "My Foundation Models session is blocking the UI" → Read:

skills/foundation-models.md

(async patterns) + also invoke

axiom-concurrency

if needed

User: "Review my Foundation Models code for issues" → Invoke:

foundation-models-auditor

agent

User: "I want to run my PyTorch model on device" → Read:

skills/ios-ml.md

(CoreML conversion, not Foundation Models)

用户："如何使用Apple Intelligence生成结构化数据？" → 查阅：

skills/foundation-models.md

用户："我的AI生成被拦截了" → 查阅：

skills/foundation-models-diag.md

用户："展示@Generable示例" → 查阅：

skills/foundation-models-ref.md

用户："实现流式AI生成" → 查阅：

skills/foundation-models.md

用户："我想给我的应用添加AI功能" → 首先询问：是Apple Intelligence（Foundation Models）还是自定义ML模型？然后相应路由。

用户："我的Foundation Models会话阻塞了UI" → 查阅：

skills/foundation-models.md

（异步模式）+ 必要时同时调用

axiom-concurrency

用户："检查我的Foundation Models代码是否有问题" → 调用：

foundation-models-auditor

代理

用户："我想在设备上运行我的PyTorch模型" → 查阅：

skills/ios-ml.md

（CoreML转换，不属于Foundation Models）