Instructor Structured LLM Outputs
Orchestra-Research/AI-Research-SKILLs
Shows how to pull validated, typed data out of LLM responses with Instructor and Pydantic models, including retries on failure and partial streaming.
A skill your agent uses when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for…
Install Foundation Models
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install johnrogers/claude-swift-engineering foundation-models --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .claude/skills/foundation-models && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .claude/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-modelsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install johnrogers/claude-swift-engineering foundation-models --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .agents/skills/foundation-models && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .agents/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install johnrogers/claude-swift-engineering foundation-models --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .cursor/skills/foundation-models && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .cursor/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/johnrogers/claude-swift-engineering.git --path plugins/swift-engineering/skills/foundation-models--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install johnrogers/claude-swift-engineering foundation-models --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .gemini/skills/foundation-models && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .gemini/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install johnrogers/claude-swift-engineering foundation-modelsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .github/skills/foundation-models && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .github/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install johnrogers/claude-swift-engineering foundation-models --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnrogers/claude-swift-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/swift-engineering/skills/foundation-models .opencode/skills/foundation-models && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "foundation-models" agent skill from https://github.com/johnrogers/claude-swift-engineering/tree/main/plugins/swift-engineering/skills/foundation-models into .opencode/skills/foundation-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "foundation-models", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
foundation-models- GitHub stars
- 231
- Token cost
- ~869 tokens
- SKILL.md length
- 375 words
- Files
- 6 (incl. references)
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for…
- Works in 5 steps: Check availability with… → Create LanguageModelSession with… → Choose output type: plain String or… → …
- Implementing on-device AI with Apples Foundation Models framework (iOS 26+)
- SKILL.md covers Overview, Reference Loading Guide, Core Workflow and Model Capabilities, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Foundation Models is an agent skill from johnrogers/claude-swift-engineering. Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/getting-started.md`, `references/streaming.md` and `references/structured-output.md`).
It sits in AI & LLM Engineering, covering Structured output and tool calling, Summarization and Type safety. It works with iOS. The repository describes itself as: A collection of agents and skills to aid in the planning, implementation, documentation and testing of Swift/TCA code. The licence is MIT.
When your agent uses it
- Implementing on-device AI with Apples Foundation Models framework (iOS 26+)
- Building summarization/extraction/classification features
- Using @Generable for type-safe structured output
Example prompts
- “/foundation-models”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Check availability with SystemLanguageModel.default.availability
- Create LanguageModelSession with optional instructions
- Choose output type: plain String or @Generable struct
- Use streaming for long generations (>1 second)
- Handle errors: context overflow, guardrails, unsupported language
What it can do on your machine
Read from SKILL.md and the folder at commit 1dc2cf4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Foundation Models loads about 869 tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 375 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from johnrogers/claude-swift-engineering at commit 1dc2cf4, republished under its MIT licence (© johnrogers). 375 words, ~869 tokens.
Download SKILL.mdSave it as
.claude/skills/foundation-models/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- foundation-models
- description
- Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
Foundation Models
Apple's on-device AI framework providing access to a 3B parameter language model for summarization, extraction, classification, and content generation. Runs entirely on-device with no network required.
Overview
Foundation Models enable intelligent text processing directly on device without server round-trips, user data sharing, or network dependencies. The core principle: leverage on-device AI for specific, contained tasks (not for general knowledge).
Reference Loading Guide
ALWAYS load reference files if there is even a small chance the content may be required. It's better to have the context than to miss a pattern or make a mistake.
| Reference | Load When |
|---|---|
| Getting Started | Setting up LanguageModelSession, checking availability, basic prompts |
| Structured Output | Using @Generable for type-safe responses, @Guide constraints |
| Tool Calling | Integrating external data (weather, contacts, MapKit) via Tool protocol |
| Streaming | AsyncSequence for progressive UI updates, PartiallyGenerated types |
| Troubleshooting | Context overflow, guardrails, errors, anti-patterns |
Core Workflow
- Check availability with
SystemLanguageModel.default.availability - Create
LanguageModelSessionwith optional instructions - Choose output type: plain String or @Generable struct
- Use streaming for long generations (>1 second)
- Handle errors: context overflow, guardrails, unsupported language
Model Capabilities
| Use Case | Foundation Models? | Alternative |
|---|---|---|
| Summarization | Yes | - |
| Extraction (key info) | Yes | - |
| Classification | Yes | - |
| Content tagging | Yes (built-in adapter) | - |
| World knowledge | No | ChatGPT, Claude, Gemini |
| Complex reasoning | No | Server LLMs |
Platform Requirements
- iOS 26+, macOS 26+, iPadOS 26+, visionOS 26+
- Apple Intelligence-enabled device (iPhone 15 Pro+, M1+ iPad/Mac)
- User opted into Apple Intelligence
Show full SKILL.md (142 more words)Show less
Common Mistakes
Using Foundation Models for world knowledge — The 3B model is trained for on-device tasks only. It won't know current events, specific facts, or "who is X". Use ChatGPT/Claude for that. Keep prompts to: summarizing user's own content, extracting info, classifying text.
Blocking the main thread — LanguageModelSession calls must run on a background thread or async context. Blocking the main thread locks UI. Always use
Task { }or background queue.Ignoring context overflow — The model has finite context. If the user pastes a 50KB document, it will fail silently or truncate. Check input length and trim/truncate proactively.
Forgetting to check availability — Not all devices support Foundation Models. Check
SystemLanguageModel.default.availabilitybefore using. Graceful degradation is required.Ignoring guardrails — The model won't answer harmful queries. Instead of fighting it, design prompts that respect safety guidelines. Rephrasing requests usually works.
© johnrogers, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in plugins/swift-engineering/skills/foundation-models of johnrogers/claude-swift-engineering.
- SKILL.md
- references/getting-started.md
- references/streaming.md
- references/structured-output.md
- references/tool-calling.md
- references/troubleshooting.md
Open the folder on GitHubat commit 1dc2cf4
Compare with similar skills
Foundation Models next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Foundation Models this skilljohnrogers/claude-swift-engineering | 231 | — | ~869 | Automated safety check: Pass | MIT | |
| Instructor Structured LLM OutputsOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~4.2k | Automated safety check: Pass | MIT | |
| Vss Benchmark Vlm QANVIDIA-AI-Blueprints/video-search-and-summarization | 1.9k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Foundation Models On Devicemajiayu000/claude-skill-registry | 666 | 5 repos | ~2k | Automated safety check: Pass | MIT | |
| Swift Mlx Lmkellyvv/PhoneClaw | 1.3k | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Outlines Structured GenerationOrchestra-Research/AI-Research-SKILLs | 13k | 10 repos | ~4k | Automated safety check: Pass | MIT |
Similar skills
Vss Benchmark Vlm QA
NVIDIA-AI-Blueprints/video-search-and-summarization
Benchmark video Q&A accuracy and latency of a deployed RT-VLM (Cosmos Reason 3) via vss vlm run, using questions and videos from the DSS vss-devx-base dataset.
Foundation Models On Device
majiayu000/claude-skill-registry
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
Swift Mlx Lm
kellyvv/PhoneClaw
MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX.
Outlines Structured Generation
Orchestra-Research/AI-Research-SKILLs
Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.
Tanstack AI
secondsky/claude-skills
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama.
More from johnrogers/claude-swift-engineering
All 17 skills in this repoLocalization
johnrogers/claude-swift-engineering
A skill your agent uses when implementing internationalization (i18n), String Catalogs, pluralization, or right-to-left layout support.
Storekit
johnrogers/claude-swift-engineering
A skill your agent uses when implementing in-app purchases, StoreKit 2 subscriptions, consumables, non-consumables, or transaction handling.
Swift Style
johnrogers/claude-swift-engineering
Swift code style conventions for clean, readable code. An agent skill from johnrogers/claude-swift-engineering.
Composable Architecture
johnrogers/claude-swift-engineering
A skill your agent uses when building features with TCA (The Composable Architecture), structuring reducers, managing state, handling effects, navigation, or testing TCA features.
Grdb
johnrogers/claude-swift-engineering
A skill your agent uses when writing raw SQL with GRDB, complex joins across 4+ tables, window functions, ValueObservation for reactive queries, or dropping down from SQLiteData for performance.
Haptics
johnrogers/claude-swift-engineering
A skill your agent uses when adding haptic feedback for user confirmations (button presses, toggles, purchases), error notifications, or custom tactile patterns (Core Haptics).
Related
Works with
Categories
Questions about Foundation Models
What does Foundation Models do?
A skill your agent uses when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for…. Foundation Models is an agent skill from johnrogers/claude-swift-engineering. Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
When should I use Foundation Models?
Foundation Models fits situations like: implementing on-device AI with Apples Foundation Models framework (iOS 26+); building summarization/extraction/classification features; using @Generable for type-safe structured output.
How do I install Foundation Models in Claude Code?
Run `npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a claude-code`. Or copy the skill folder (plugins/swift-engineering/skills/foundation-models in johnrogers/claude-swift-engineering) into .claude/skills/foundation-models in your project. Claude Code loads it when a task matches its description.
How do I install Foundation Models in Codex?
Run `npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a codex`. Or copy the skill folder (plugins/swift-engineering/skills/foundation-models in johnrogers/claude-swift-engineering) into .agents/skills/foundation-models in your project. Codex loads it when a task matches its description.
Can I use Foundation Models in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/foundation-models, .gemini/skills/foundation-models, .github/skills/foundation-models and .opencode/skills/foundation-models in your project.
What does Foundation Models need to run?
SKILL.md names no scripts, command-line tools or credentials: Foundation Models is instructions for the agent only.
Does Foundation Models access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Foundation Models safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Foundation Models use?
Foundation Models is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Foundation Models use?
About 869 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.
What are the alternatives to Foundation Models?
Skills that share tags, products or a category with Foundation Models: Instructor Structured LLM Outputs (Orchestra-Research/AI-Research-SKILLs, 13k stars), Vss Benchmark Vlm QA (NVIDIA-AI-Blueprints/video-search-and-summarization, 1.9k stars), Foundation Models On Device (majiayu000/claude-skill-registry, 666 stars) and Swift Mlx Lm (kellyvv/PhoneClaw, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Foundation Models?
johnrogers (a GitHub user) maintains it in johnrogers/claude-swift-engineering, which has 231 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on January 18, 2026.
Source: johnrogers/claude-swift-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.