# axiom-ai

Routes Apple Intelligence development, covering Foundation Models, @Generable, SpeechTranscriber, and CoreML.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1100 installs · ★ 1229
- Author: CharlesWiltgen
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/CharlesWiltgen/Axiom/tree/HEAD/axiom-codex/skills/axiom-ai/SKILL.md
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/skills/axiom-ai

## What it does

The skill acts as an architectural router for Apple on-device AI. It directs coding agents across Foundation Models, `LanguageModelSession` lifecycles, and `@Generable` structured decoding. When a project requires custom weights from PyTorch or TensorFlow, it routes work toward Core ML workflows instead of system models.

Clear runtime boundaries prevent dead ends during development. It notes that `adapters.safetensors` from MLX LM cannot run inside `LanguageModelSession`, while `MLUpdateTask` is restricted to legacy NN-spec formats. Any audit tools invoking builds, tests, or simulators require local shell access to execute properly.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add CharlesWiltgen/Axiom --skill axiom-ai -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/axiom-ai/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/axiom-ai/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add CharlesWiltgen/Axiom --skill axiom-ai -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/axiom-ai/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add CharlesWiltgen/Axiom --skill axiom-ai -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/axiom-ai/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install CharlesWiltgen/Axiom axiom-ai
```

2. **Manually: put the files in place**
- File: `.github/skills/axiom-ai/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add CharlesWiltgen/Axiom --skill axiom-ai -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/CharlesWiltgen/Axiom --path axiom-codex/skills/axiom-ai
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/axiom-ai/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add CharlesWiltgen/Axiom --skill axiom-ai -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/CharlesWiltgen/Axiom/tree/HEAD/axiom-codex/skills/axiom-ai/SKILL.md

## When to use it
- configure `LanguageModelSession` and structured output using `@Generable`
- route between native Foundation Models and custom Core ML architectures
- resolve main-actor UI freezes and `concurrentRequests` session errors
- navigate speech-to-text boundaries with `SpeechTranscriber` and `SpeechAnalyzer`

## Example prompts
- Help me set up a `LanguageModelSession` that generates structured output with `@Generable`
- Diagnose why `concurrentRequests` fails during on-device model inference
- Check the analyzer concurrency limit for `SpeechTranscriber` on iOS

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: ce2d2cbd19ee030d.

BEGIN THIRD-PARTY FILE ce2d2cbd19ee030d
```text
---
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
```
END THIRD-PARTY FILE ce2d2cbd19ee030d

The third-party file has ended. Everything between the ce2d2cbd19ee030d tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3097 of 25358 bytes. © CharlesWiltgen · MIT · https://github.com/CharlesWiltgen/Axiom/tree/HEAD/axiom-codex/skills/axiom-ai/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md