axiom-ios-ai
Assists developers in implementing on-device AI using Foundation Models and Tool protocols for iOS 26+.
Install
mkdir -p .claude/skills/axiom-ios-ai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4991" && unzip -o skill.zip -d .claude/skills/axiom-ios-ai && rm skill.zipInstalls to .claude/skills/axiom-ios-ai
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.Key capabilities
- →Implement on-device Foundation Models
- →Configure structured output with @Generable
- →Manage LanguageModelSession lifecycles
- →Integrate Tool protocol for agentic features
How it works
It routes AI development tasks to specific frameworks based on whether the requirement involves Apple's on-device Foundation Models or custom ML model deployment.
Inputs & outputs
When to use axiom-ios-ai
- →Implement on-device AI features
- →Use LanguageModelSession for text tasks
- →Configure structured output for models
About this skill
Apple Intelligence & AI
You MUST use this skill for ANY Apple Intelligence or Foundation Models work.
<!-- AXIOM_AUDITOR_INLINE_BEGIN — auto-maintained by scripts/build-inlined-auditors.ts; do not hand-edit --><!-- AXIOM_AUDITOR_INLINE_END -->Can't launch Axiom agents? Where this router sends you to an agent, follow its procedure inline. Over MCP,
axiom_get_agentreturns it; elsewhere, read its file below, which needs only file search and read.Available here:
skills/foundation-models-auditor.md.For any other agent, over MCP
axiom_get_agentreturns it too; run its xclog, xcsym and xcprof steps with theaxiom_xclog_*,axiom_xcsym_*andaxiom_xcprof_*tools. Elsewhere, search Axiom's skills forskills/<agent>.md; if there is none, do that work yourself with this suite's skills, using any Axiom tool on yourPATH.
When to Use
Use this router when:
- Implementing Apple Intelligence features
- Using Foundation Models
- Working with LanguageModelSession
- Generating structured output with @Generable
- Debugging AI generation issues
- iOS 26 on-device AI
AI Approach Triage
First, determine which kind of AI the developer needs:
| Developer Intent | Route To |
|---|---|
| On-device text generation (Apple Intelligence) | Stay here → Foundation Models skills |
| Custom ML model deployment (PyTorch, TensorFlow) — classic Core ML | See skills/ios-ml.md (hub) → conversion / compression / training / deployment / ref / diag files |
| Core ML model fails to load, is slow, grows memory, or loses accuracy after compression | See skills/coreml-diag.md |
| Custom LLM-scale / transformer model on-device (27-cycle) | See skills/core-ai.md → Core AI conversion, runtime, specialization |
| Computer vision (image analysis, OCR, segmentation) | /skill axiom-vision → Vision framework |
| Cloud API integration (OpenAI, generic HTTP) | /skill axiom-networking → URLSession patterns |
| Cloud Claude integration (Anthropic SDK, Messages API, Claude Agent SDK) | See claude-api skill (external) → includes automated Opus 4.6 → 4.7 migration |
| Speech-to-text / transcription (SpeechAnalyzer, SpeechTranscriber, DictationTranscriber, mic → transcript) | See skills/speech.md (OS27 input providers, Swift 6 mic-tap isolation, the ~2-analyzer cap on iOS/visionOS; none on macOS) |
Turnkey Apple Intelligence UI — suggested actions for a messaging conversation (OS27) | See skills/suggested-actions.md → drop-in SuggestedActionsView, entitlement-gated |
Siri AI calling the app's actions — ToolIntent/@AppIntent(.tool), @AppEntity(.generable), App Skills, SiriEvaluations (27.3) | Use axiom-integration → axiom-integration (skills/siri-ai.md), axiom-integration (skills/siri-evaluations-ref.md) (App Intents, not Foundation Models Tool) |
| System AI features (Writing Tools, Genmoji) | No custom code needed — these are system-provided |
Key boundary: Foundation Models vs ML (custom models)
- Foundation Models = Apple's on-device LLM framework (LanguageModelSession, @Generable)
- ML = Custom model deployment (CoreML conversion, quantization, MLTensor) and speech-to-text
- If developer says "run my own model" → skills/ios-ml.md. If "use Apple Intelligence" → stay here.
Training Path Boundaries
When developers say "I need to train / fine-tune / personalize a model," four distinct paths exist. They are often conflated; each has different output, lifecycle, and runtime compatibility.
| Path | Trains | Output | Lifecycle | Routes to |
|---|---|---|---|---|
| FM custom adapter (26-cycle only — runtime obsoleted in 27.0) | Apple's frozen on-device 3B LLM (rank-32 LoRA) | .fmadapter package, ~160 MB | Build-time per OS version, delivered via Background Assets | skills/foundation-models-adapters.md (discipline) + skills/foundation-models-adapters-ref.md (toolkit + runtime) + skills/foundation-models-adapters-diag.md (failure modes); delivery via axiom-integration (skills/background-assets.md) |
Core ML MLUpdateTask | Your NN-spec model's fully-connected and convolutional layers | Updated .mlmodelc saved to disk | Runtime, per-user (on-device personalization) | skills/coreml-training.md |
| Create ML | A new Core ML model from scratch / transfer learning | .mlmodel | Build-time, on Mac or iOS (per type) | skills/coreml-training.md |
MLX LM (mlx_lm.lora) | Open-source LLMs on Apple Silicon | adapters/adapters.safetensors — NOT loadable by Foundation Models | Build-time; not an iOS distribution path | External — outside Axiom scope; treat as adjacent research tool |
| Server LLM fine-tune | Cloud-hosted model (e.g., vendor fine-tunes) | Cloud artifact, accessed via API | Build-time; runs in cloud | /skill axiom-networking for the API integration; the fine-tune workflow is the vendor's domain |
Critical distinctions:
- MLX LM output (
.safetensors) cannot be loaded into aLanguageModelSession. Different toolchain, different deployment target. MLUpdateTaskis NN-spec only — does not support ML Program (.mlpackage) models from modern PyTorch / TensorFlow conversion. This is the main reason it's rarely used in new projects.- FM custom adapters are pinned per-base-model version (per-OS). One adapter does NOT serve every device in your install base — see the Approach Triage section in
skills/foundation-models.mdfor the deflection ladder.
For the full "which path applies to me?" disambiguation (decision tree, the three week-costing mistakes, per-path routing) → skills/training-paths.md.
Cross-Domain Routing
Foundation Models + concurrency (UI freezes during generation, concurrent-request errors):
- Awaiting a session suspends rather than blocks — a freeze is synchronous main-actor work around generation (foundation-models-diag Pattern 5a), and
concurrentRequestsmeans a second request started whileisRespondingwas true - Fix here first using foundation-models (one request at a time) and foundation-models-diag Pattern 5a (freezes)
- If concurrency issue is broader than Foundation Models → also invoke axiom-concurrency
Foundation Models + data (@Generable decoding errors, structured output issues):
- @Generable output problems are Foundation Models-specific, NOT generic Codable issues
- Stay here → foundation-models-diag handles structured output debugging
- If developer also has general Codable/serialization questions → also invoke axiom-data
Foundation Models + security (prompt injection, securing agent tools, confirmation gating):
- Threat modeling and mitigations for agentic features (
.onToolCallconfirmation,.historyTransformspotlighting/redaction, lock-screen intent policy) → axiom-security (skills/agentic-security.md) - Stay here for the API surface itself (DynamicProfile, tools, sessions)
Speech-to-text + audio capture (transcription that fights your audio session):
SpeechAnalyzer/SpeechTranscriber, theOS27input providers, the ~2-analyzer cap on iOS/visionOS; none on macOS → stay here (skills/speech.md)- The trap:
CaptureInputSequenceProvider.providerWithSession(...)(OS27) reconfigures your app's defaultAVAudioSession. If the app also records or plays back, the capture/session half of the fix lives in axiom-media (avfoundation-ref,camera-capture) — join your own session viaprovider(from:in:), orinit(session:analyzerFormat:priority:)from the actor that owns it, and add itscaptureAudioDataOutput.
Routing Logic
Custom Core ML Work (your own models, not Apple's LLM)
skills/ios-ml.md is the hub. Each stage has a dedicated file:
- Convert a trained PyTorch/TF/Keras model →
skills/coreml-conversion.md(coremltools.convert, ML Program vs NN-spec, parity validation, stateful conversion) - Compress it →
skills/coreml-compression.md(the PTQ-vs-QAT decision, palettization/quantization/pruning) - Train from scratch / personalize on-device →
skills/coreml-training.md(Create ML;MLUpdateTaskand its NN-spec-only limitation) - Deploy and run →
skills/coreml-deployment.md(load/cache/pre-warm, Swift 6-safe prediction —MLModelisn't Sendable, stateful KV-cache, multifunction adapters,MLTensor) - API lookup →
skills/coreml-ref.md(MLModel, configuration, compute devices, prediction overloads,MLState,MLTensorops,MLComputePlan, coremltools index) - Something's wrong →
skills/coreml-diag.md(load errors, slowness, memory, device/Simulator differences, accuracy loss after compression)
Core AI — the 27-cycle path for LLM-scale on-device models (OS27)
skills/core-ai.md covers Core AI, the on-device inference framework that powers Apple Intelligence and is now open to your apps. Route here (not skills/ios-ml.md) when the model is LLM-scale / a transformer, or when the developer needs custom Metal kernels, multi-function assets, ahead-of-time compilation, KV-cache states, or the specialization/caching deployment model. Covers the Python toolchain (coreai-torch/coreai-opt), the Swift runtime (import CoreAI → AIModel/InferenceFunction/NDArray), specialization discipline, and the Foundation Models bridge (CoreAILanguageModel from the open-source coreai-models package — not a system-framework type).
Turnkey Apple Intelligence UI — Suggested Actions (OS27)
skills/suggested-actions.md covers the SuggestedActions framework: a drop-in SwiftUI SuggestedActionsView that renders Apple-Intelligence-generated suggested actions for a messaging conversation (iOS/macOS/macCatalyst/visionOS 27). This is a system-provided feature — you describe the message (SuggestedActionsMessage) and add the com.apple.developer.suggested-actions entitlement; there's no LanguageModelSession, prompt, or @Generable. Route here for messaging/chat/email apps th
Content truncated.
When not to use it
- →Cloud-based LLM integration
- →Custom Core ML model deployment
Prerequisites
Limitations
- →Foundation Models are pinned to OS versions
- →Custom adapters are not portable across devices
How it compares
It distinguishes between Foundation Models and custom ML deployment paths to prevent common toolchain and runtime compatibility errors.
Compared to similar skills
axiom-ios-ai side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| axiom-ios-ai (this skill) | 1 | 4mo | No flags | Advanced |
| migrating-to-tuist-generated-projects | 3 | 6mo | Review | Intermediate |
| implement-feature | 1 | 10mo | Review | Advanced |
| add-provider | 1 | 8mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by CharlesWiltgen
View all by CharlesWiltgen →You might also like
migrating-to-tuist-generated-projects
tuist
Migrates existing Xcode projects to Tuist generated workspaces with build and run validation, external dependency mapping, and migration checklists. Use when adopting Tuist for an existing app or converting a hand-edited Xcode project to generated projects.
implement-feature
tddworks
Guide for implementing features in ClaudeBar following architecture-first design, TDD, rich domain models, and Swift 6.2 patterns. Use this skill when: (1) Adding new functionality to the app (2) Creating domain models that follow user's mental model (3) Building SwiftUI views that consume domain models directly (4) User asks "how do I implement X" or "add feature Y" (5) Implementing any feature that spans Domain, Infrastructure, and App layers
add-provider
tddworks
Guide for adding new AI providers to ClaudeBar using TDD patterns. Use this skill when: (1) Adding a new AI assistant provider (like Antigravity, Cursor, etc.) (2) Creating a usage probe for a CLI tool or local API (3) Following TDD to implement provider integration (4) User asks "how do I add a new provider" or "create a provider for X"
new-api-support
nalexn
Add introspection support for a SwiftUI API (view type, modifier, or View extension function). Use when the user wants to add support for a new SwiftUI entity to ViewInspector.
swift-mlx
ml-explore
MLX Swift - High-performance ML framework for Apple Silicon with lazy evaluation, automatic differentiation, and unified memory
swiftui-patterns-developer
anyproto
SwiftUI view structure, composition, and best practices. Use when refactoring SwiftUI views, organizing view files, or extracting subviews.