axiom-ai

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

| "Permissive mode disables guardrails" | It relaxes layer 2 for string transformations only. Input/output guardrails for guided generation, your instructions, prompt hygiene, and use-case mitigations

Audit 0.4.1 · source sha 59e2d18fd914 · 21 Oct 2026Report an issue or request a re-scan

• Publishercharleswiltgen GitHub userOwner of the repository this skill is read from
• Source foldercharleswiltgen/axiom/axiom-codex/skills/axiom-aiThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict59e2d18fd914A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: 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…

---
name: axiom-ai
description: 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.
license: MIT
---

# Apple Intelligence & AI

**You MUST use this skill for ANY Apple Intelligence or Foundation Models work.**

<!-- AXIOM_AUDITOR_INLINE_BEGIN — rewritten for Codex by scripts/build-codex.ts; do not hand-edit -->
> **Auditors are skills here.** Where this router says "Launch `some-auditor` agent", invoke the
> matching Codex skill instead — same procedure, no Claude Code agent required.
>
> Available: `axiom-audit-foundation-models`.
>
> The ones that shell out — builds, tests, simulators, crash symbolication — need shell access to run.
<!-- AXIOM_AUDITOR_INLINE_END -->

## 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 |
| 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 a `LanguageModelSession`. Different toolchain, different deployment target.
- `MLUpdateTask` is **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.md` for 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 `concurrentRequests` means a second request started while `isResponding` was 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 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-21
   ✓SAFE B 89 / 100

   first audit · source 59e2d18fd914

Questions about axiom-ai

• github.com/charleswiltgen/axiom/tree/main/axiom-codex/skills/axi — the audited source at commit 59e2d18fd914 and every finding aboveObserved · 21 Oct 2026

Spotted something wrong? Report a correction · Methodology