On Device AI

Build iOS 26+ apps with Apple's Foundation Models framework for on-device AI. Use when implementing @Generable structured output, LanguageModelSession, Tool protocol, streaming responses, or any on-device LLM integration. Covers the 3B parameter model available on M1+ devices with Apple Intelligence enabled.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add 199-biotechnologies/swiftui-claude-skills --skill on-device-ai
Manual install
git clone --depth 1 https://github.com/199-biotechnologies/swiftui-claude-skills.git /tmp/swiftui-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/swiftui-claude-skills/on-device-ai ~/.claude/skills/on-device-ai

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# On-Device AI with Foundation Models (iOS 26+)

Build intelligent features using Apple's on-device 3B parameter LLM — free, offline, private.

## Requirements
- iOS 26+ / macOS Tahoe 26+ / iPadOS 26+
- Apple Silicon (M1 or newer)
- Apple Intelligence enabled on device
- `import FoundationModels`

## Core API

### Basic Text Generation
```swift
import FoundationModels

let session = LanguageModelSession()
let response = try await session.respond(to: "Summarize this article in 3 bullets")
print(response.content) // String
```

### Streaming Responses
```swift
let stream = session.streamResponse(to: "Explain quantum computing")
for try await partial in stream {
    print(partial.content) // Incremental text
}
```

### Structured Output with @Generable
```swift
@Generable
struct RecipeSuggestion {
    var name: String
    var ingredients: [String]
    var cookingTimeMinutes: Int
    var difficulty: Difficulty

    enum Difficulty: String, Generable {
        case easy, medium, hard
    }
}

let session = LanguageModelSession()
let recipe: RecipeSuggestion = try await session.respond(
    to: "Suggest a quick pasta recipe",
    generating: RecipeSuggestion.self
)
```

### Guided Generation with @Guide
```swift
@Guide("Generate a haiku about nature")
struct NatureHaiku {
    @Guide("First line, 5 syllables")
    var line1: String
    @Guide("Second line, 7 syllables")
    var line2: String
    @Guide("Third line, 5 syllables")
    var line3: String
}
```

### Tool Calling
Read the full skill on GitHub

Details

Skill name
on-device-ai
Path
on-device-ai/SKILL.md
Repo updated
19 March 2026

FAQ

What does the On Device AI skill do?

Build iOS 26+ apps with Apple's Foundation Models framework for on-device AI. Use when implementing @Generable structured output, LanguageModelSession, Tool protocol, streaming responses, or any on-device LLM integration. Covers the 3B parameter model available on M1+ devices with Apple Intelligence enabled.

How do I install the On Device AI skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 199-biotechnologies/swiftui-claude-skills --skill on-device-ai. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is On Device AI popular?

It lives in 199-biotechnologies/swiftui-claude-skills, which has 9 GitHub stars and 0 forks.

Related skills

Swift Concurrency Pro

9

199-biotechnologies/swiftui-claude-skills

Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.

Mobile Development

Swiftui Liquid Glass

9

199-biotechnologies/swiftui-claude-skills

Implement, review, or improve SwiftUI features using the iOS 26+ Liquid Glass API. Use when asked to adopt Liquid Glass in new SwiftUI UI, refactor an existing feature to Liquid Glass, or review Liquid Glass usage for correctness, performance, and design alignment.

Mobile Development

Swiftui UI Patterns

9

199-biotechnologies/swiftui-claude-skills

Best practices and example-driven guidance for building SwiftUI views and components. Use when creating or refactoring SwiftUI UI, designing tab architecture with TabView, composing screens, or needing component-specific patterns and examples.

Frontend & Design

Context Consultant

8

hex-inc/hex-skills

Use to build, manage, and improve the context that makes Hex's AI agents (Threads, the Notebook Agent, the Modeling Agent) accurate — endorsements & exclusions, warehouse descriptions, workspace context & guides, and semantic models. Covers standing context up from scratch, measuring it with a dedicated eval engine (authoring and running eval suites, sourcing cases from real usage, gating changes in a preview), reviewing Context Studio Suggestions, and publishing via GitHub sync or the Hex CLI. Triggers on: "context management", "manage my Hex context", "context strategy", "context engineering

AI, LLMs & Agents

No AI Slop

6

nehasu19/job-radar

Write like a sharp human professional, not a chatbot. Use whenever drafting or editing text someone will send or publish as their own — resumes, CVs, cover letters, LinkedIn posts, emails, bios, application answers, reports. Strips generic filler, buzzwords, inflated claims and tell-tale AI phrasing, and keeps only content that is specific, true and relevant to the reader.

AI, LLMs & Agents

Crossborder Ecom Ops

9

xianglouw/ecom-agent-skills

跨境电商多平台运营端到端工作流总控技能,负责阶段路由与人机协作编排:把「规则检索 → 表格整理 → 选品测算 → 视频素材 → 广告投流 → PO 单 → ROI 复盘」七个阶段串成一条流水线,另含线下门店手写单据台账支线,统一输出信封、风险分级、人机边界与 Prompt 六段式框架,并按阶段调用 ecom-rules-fee、ecom-data-prep、ecom-selection-profit、ecom-video-creative、ecom-ads-plan、ecom-po-build、ecom-roi-review、ecom-receipt-ledger 等专项技能。涉及 Amazon、Shopee、TikTok Shop、Temu、Lazada、Wayfair、美客多、独立站等多平台运营时,若用户在问「运营全链路怎么搭」「从选品到复盘跑一遍」「这套 Agent 工作流怎么落地」「团队 SOP 与 Prompt 模板怎么沉淀」,或一次提出跨阶段任务,用本技能做编排。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.