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.
Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp.
Install Apple On Device AI
$ npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dpearson2699/swift-ios-skills apple-on-device-ai --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/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/apple-on-device-ai .claude/skills/apple-on-device-ai && 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 "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .claude/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-aiType 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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dpearson2699/swift-ios-skills apple-on-device-ai --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/apple-on-device-ai .agents/skills/apple-on-device-ai && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .agents/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dpearson2699/swift-ios-skills apple-on-device-ai --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/apple-on-device-ai .cursor/skills/apple-on-device-ai && 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 "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .cursor/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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/dpearson2699/swift-ios-skills.git --path skills/apple-on-device-ai--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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dpearson2699/swift-ios-skills apple-on-device-ai --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/apple-on-device-ai .gemini/skills/apple-on-device-ai && 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 "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .gemini/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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 dpearson2699/swift-ios-skills apple-on-device-aiInstalls 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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/apple-on-device-ai .github/skills/apple-on-device-ai && 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 "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .github/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dpearson2699/swift-ios-skills apple-on-device-ai --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/apple-on-device-ai .opencode/skills/apple-on-device-ai && 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 "apple-on-device-ai" agent skill from https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/apple-on-device-ai into .opencode/skills/apple-on-device-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apple-on-device-ai", 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
apple-on-device-ai- GitHub stars
- 1.2k
- Token cost
- ~3.4k tokens
- SKILL.md length
- 1,347 words
- Files
- 6 (incl. references)
- Skills in repo
- 86
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp.
- Works in 5 steps: Freeze representative source-model… → Convert, then run the same fixtures… → If output parity or task metrics miss… → …
- Choosing an Apple-local model runtime
- SKILL.md covers Contents, Framework Selection Router, Apple Foundation Models Overview and Core ML Overview, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Apple On Device AI is an agent skill from dpearson2699/swift-ios-skills. Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp. Use when choosing an Apple-local model runtime, building an Apple Intelligence chatbot or tool-calling feature, running an LLM on Apple Silicon, converting or compressing a Python model for Core ML, or comparing on-device inference backends. For Swift Core ML loading and prediction code, use the coreml skill.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `evals/evals.json`, `references/coreml-conversion.md` and `references/coreml-optimization.md`).
It sits in AI & LLM Engineering, covering iOS development, LLM inference and serving and Structured output and tool calling. It works with llama.cpp and Python. The repository describes itself as: Agent Skills for iOS 26+, Swift 6.3, SwiftUI, and modern Apple frameworks.
When your agent uses it
- Choosing an Apple-local model runtime
- Building an Apple Intelligence chatbot
- Tool-calling feature
- Running an LLM on Apple Silicon
Example prompts
- “/apple-on-device-ai”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Freeze representative source-model fixtures and acceptable output/task
- Convert, then run the same fixtures through the source and Core ML models.
- If output parity or task metrics miss tolerance, inspect shapes, operators,
- Compress only after the uncompressed model passes. Revalidate accuracy after
- Profile the passing model on physical target devices, then repeat until
What it can do on your machine
Read from SKILL.md and the folder at commit 8d90fd1. 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 (its code samples are swift and python).
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
Apple On Device AI loads about 3.4k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,347 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,347 words (~3,423 tokens).
“Guide for selecting, deploying, and optimizing on-device ML models. Covers Apple Foundation Models, Core ML, MLX Swift, and llama.cpp.”
- name
- apple-on-device-ai
Files
SKILL.md and 5 other files (references) in skills/apple-on-device-ai of dpearson2699/swift-ios-skills.
- SKILL.md
- evals/evals.json
- references/coreml-conversion.md
- references/coreml-optimization.md
- references/foundation-models.md
- references/mlx-swift.md
Open the folder on GitHubat commit 8d90fd1
Compare with similar skills
Apple On Device AI 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 |
|---|---|---|---|---|---|---|
| Apple On Device AI this skilldpearson2699/swift-ios-skills | 1.2k | — | ~3.4k | Automated safety check: Pass | Custom licence | |
| Outlines Structured GenerationOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~4k | Automated safety check: Pass | MIT | |
| Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Aqua Deploymentoracle/accelerated-data-science | 125 | — | ~2.4k | Automated safety check: Pass | UPL-1.0 | |
| Guidance Constrained GenerationOrchestra-Research/AI-Research-SKILLs | 13k | 5 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Gguf QuantizationOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Qwen Mtp Gguf
R6410418/Jackrong-llm-finetuning-guide
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
- Official
Aqua Deployment
oracle/accelerated-data-science
Deploy LLM models on OCI using AI Quick Actions (AQUA) - single model, multi-model, stacked (LoRA), with GPU shape selection, vLLM configuration, streaming, and tool calling.
Guidance Constrained Generation
Orchestra-Research/AI-Research-SKILLs
Constrains language model output with regex, selections and grammars using the Guidance library, so JSON, XML, code or formatted fields come out valid.
Gguf Quantization
Orchestra-Research/AI-Research-SKILLs
GGUF format and llama.cpp quantization for efficient CPU/GPU inference.
- Official
Aqua Model Lifecycle
oracle/accelerated-data-science
Register, list, get, and manage LLM models in OCI AI Quick Actions (AQUA) using the ADS SDK.
More from dpearson2699/swift-ios-skills
All 86 skills in this repoiOS Memgraph Analysis
dpearson2699/swift-ios-skills
A skill your agent uses when capturing or analyzing an iOS .memgraph, especially when the task mentions a memory leak, heap growth, persistent memory increase, ownership path, or matched-capture…
iOS Ettrace Performance
dpearson2699/swift-ios-skills
A skill your agent uses when capturing or analyzing ETTrace profiles for a focused iOS launch or runtime flow, including exact-build dSYM UUID matching, Simulator or device capture, processed…
Accessorysetupkit
dpearson2699/swift-ios-skills
Discover and configure Bluetooth and Wi-Fi accessories using AccessorySetupKit.
Activitykit
dpearson2699/swift-ios-skills
Implement, review, or improve Live Activities and Dynamic Island experiences in iOS apps using ActivityKit.
Adattributionkit
dpearson2699/swift-ios-skills
Measure ad effectiveness with privacy-preserving attribution using AdAttributionKit.
Alarmkit
dpearson2699/swift-ios-skills
Implement AlarmKit alarms and countdown timers for iOS and iPadOS with Lock Screen, Dynamic Island, StandBy, and paired Apple Watch system UI.
Related
Categories
Questions about Apple On Device AI
What does Apple On Device AI do?
Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp. Apple On Device AI is an agent skill from dpearson2699/swift-ios-skills.cpp.
When should I use Apple On Device AI?
Apple On Device AI fits situations like: choosing an Apple-local model runtime; building an Apple Intelligence chatbot; tool-calling feature; running an LLM on Apple Silicon.
How do I install Apple On Device AI in Claude Code?
Run `npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a claude-code`. Or copy the skill folder (skills/apple-on-device-ai in dpearson2699/swift-ios-skills) into .claude/skills/apple-on-device-ai in your project. Claude Code loads it when a task matches its description.
How do I install Apple On Device AI in Codex?
Run `npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a codex`. Or copy the skill folder (skills/apple-on-device-ai in dpearson2699/swift-ios-skills) into .agents/skills/apple-on-device-ai in your project. Codex loads it when a task matches its description.
Can I use Apple On Device AI 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 dpearson2699/swift-ios-skills --skill apple-on-device-ai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apple-on-device-ai, .gemini/skills/apple-on-device-ai, .github/skills/apple-on-device-ai and .opencode/skills/apple-on-device-ai in your project.
What does Apple On Device AI need to run?
SKILL.md names no scripts, command-line tools or credentials: Apple On Device AI is instructions for the agent only. Our summary lists: Python 3.
Does Apple On Device AI 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 Apple On Device AI 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 Apple On Device AI use?
Apple On Device AI has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Apple On Device AI use?
About 3.4k tokens (SKILL.md is roughly 14k 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 12k tokens, read only when the agent opens those files.
What are the alternatives to Apple On Device AI?
Skills that share tags, products or a category with Apple On Device AI: Outlines Structured Generation (Orchestra-Research/AI-Research-SKILLs, 13k stars), Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars), Aqua Deployment (oracle/accelerated-data-science, 125 stars) and Guidance Constrained Generation (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Apple On Device AI?
dpearson2699 (a GitHub user) maintains it in dpearson2699/swift-ios-skills, which has 1,183 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on July 31, 2026.
Source: dpearson2699/swift-ios-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.