apple-foundation-models
Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps
What this skill does
# Apple Foundation Models Skill
## When to Use This Skill
Use this skill when you need help with:
- **On-device AI**: Building iOS/macOS apps with on-device language models
- **SystemLanguageModel**: Working with Apple's on-device LLM API
- **Guided Generation**: Generating structured Swift types from prompts
- **Tool Calling**: Extending model capabilities with custom tools
- **Prompting**: Crafting effective prompts for on-device models
- **Safety**: Implementing guardrails and handling sensitive content
- **Localization**: Supporting multilingual AI features
This skill covers iOS 26.0+, iPadOS 26.0+, macOS 26.0+, and visionOS 26.0+.
## Description
Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps. Covers SystemLanguageModel, LanguageModelSession, guided generation, tool calling, and prompting patterns.
## Quick Reference
### Core Components
### Advanced
- `Transcript`
- `Transcript.Entry`
- `Transcript.Response`
- `Transcript.ResponseFormat`
- `Transcript.Segment`
- `Transcript.StructuredSegment`
### Api Reference
- `FoundationModels`
- `GenerationID`
- `SystemLanguageModel`
- `SystemLanguageModel.Adapter`
- `SystemLanguageModel.Guardrails`
- `SystemLanguageModel.UseCase`
### Getting Started
- `SystemLanguageModel.Availability`
### Guided Generation
- `DynamicGenerationSchema`
- `Generable`
- `GenerationGuide`
- `GenerationSchema`
- `Guide`
### Localization
- `LanguageModelFeedback`
### Prompting
- `Instructions`
- `InstructionsBuilder`
- `InstructionsRepresentable`
- `LanguageModelSession`
- `LanguageModelSession.GenerationError`
- `LanguageModelSession.ToolCallError`
- `Prompt`
- `PromptBuilder`
- `PromptRepresentable`
- `Transcript.Instructions`
- `Transcript.Prompt`
### Tool Calling
- `Tool`
## Key Concepts
### Platform Support
- iOS 26.0+
- iPadOS 26.0+
- macOS 26.0+
- Mac Catalyst 26.0+
- visionOS 26.0+
### On-Device AI
All models run entirely on-device, ensuring privacy and offline capability.
## Usage Guidelines
1. Check model availability before use
2. Define clear instructions for the model's behavior
3. Use guided generation for structured outputs
4. Implement tool calling for dynamic capabilities
5. Handle errors appropriately
## Navigation
See the `references/` directory for detailed API documentation organized by category:
- `references/advanced.md` - Advanced
- `references/api_reference.md` - Api Reference
- `references/getting_started.md` - Getting Started
- `references/guided_generation.md` - Guided Generation
- `references/localization.md` - Localization
- `references/prompting.md` - Prompting
- `references/tool_calling.md` - Tool Calling
## Best Practices
- **Prompting**: Be specific and clear in your prompts
- **Instructions**: Define the model's behavior upfront
- **Safety**: Enable guardrails for sensitive content
- **Localization**: Check supported languages for your use case
- **Performance**: Use prewarm() for better response times
- **Streaming**: Use streamResponse() for real-time user feedback
## Common Patterns
### Basic Session
```swift
let model = SystemLanguageModel(useCase: .general)
let session = LanguageModelSession(model: model)
let response = try await session.respond(to: Prompt("Your question"))
```
### Guided Generation
```swift
struct Recipe: Generable {
let title: String
let ingredients: [String]
}
let recipe = try await session.respond(
generating: Recipe.self,
prompt: Prompt("Create a pasta recipe")
)
```
### Tool Calling
```swift
struct WeatherTool: Tool {
func call(arguments: String) async throws -> String {
// Fetch weather data
}
}
let session = LanguageModelSession(
model: model,
tools: [WeatherTool()]
)
```
## Reference Documentation
For complete API details, see the categorized documentation in the `references/` directory.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.