FoundationModels on-device LLM patterns (iOS 26)
Build privacy-first AI features with Apple's on-device FoundationModels: sessions, structured output with @Generable, tool calling, snapshot streaming
- What
- Build privacy-first AI features with Apple's on-device FoundationModels: sessions, structured output with @Generable, tool calling, snapshot streaming
- Cost
- Free
- Needs
- an Apple Intelligence-eligible Apple device; an Xcode/Swift project targeting iOS 26-era FoundationModels APIs
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a patterns guide by @affaan-m for integrating Apple's on-device language model into iOS apps with the FoundationModels framework (iOS 26 era): availability checks, single- and multi-turn sessions, guided generation with `@Generable` structured types, custom tool calling, and snapshot streaming for real-time UI — plus best practices and anti-patterns. Honest caveats: requires an Apple Intelligence-eligible device; the on-device context window is capped at 4,096 tokens, which shapes prompt design; iOS 26-era APIs may drift between releases; listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
FoundationModels on-device LLM patterns (iOS 26) is a free Muse skill and patterns guide for integrating Apple's on-device language model into iOS apps with the FoundationModels framework. It covers availability checks, single- and multi-turn sessions, guided generation with Generable types, custom tool calling, and snapshot streaming for real-time interfaces, plus privacy-first best practices.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an Apple Intelligence-eligible Apple device; an Xcode/Swift project targeting iOS 26-era FoundationModels APIs Install "FoundationModels on-device LLM patterns (iOS 26)" for me. Fetch the SKILL.md from the source repository into a temporary folder, review it for anything suspicious, then summarize in two or three sentences which patterns it covers (availability checks, sessions, @Generable structured output, tool calling, snapshot streaming) so I can apply them to my own Swift project. Repository: https://raw.githubusercontent.com/affaan-m/ecc/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/docs/ja-JP/skills/foundation-models-on-device/SKILL.md Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: don't touch anything outside the temp folder and the skill's own content. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 4eb71d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.