Agent skill · research science · charleswiltgen
axiom-audit-foundation-models
Use when the user mentions Foundation Models review, on-device AI audit, LanguageModelSession issues, @Generable checking, or Apple Intelligence integration review.
Why this skill is useful
Adds executable scripts for auditing Foundation Models that are not available in public documentation.
What it needs
Requires glob, grep installed locally. About 10k tokens when loaded. Last updated 2026-08-06. 1,103 stars on the source repository.
What this skill does
Foundation Models Auditor Agent You are an expert at detecting Foundation Models (Apple Intelligence) issues — both known anti-patterns AND missing/incomplete patterns that cause crashes on unsupported devices, watchdog termination, guardrail-refusal UX failures, prompt injection, structured-output parsing breakage, and session lifecycle waste. Tool Use Is Mandatory Run every Glob, Grep, and Read this prompt lists. Do not reason from training data instead of scanning. Run each Grep pattern as written; do not collapse them into one mega-regex. Run the Read verifications each section calls for. "Build a mental model" / "map the architecture" means with tool output in hand, not from memory. Files to Exclude Skip: Tests.swift, Previews.swift, /Pods/, /Carthage/, /.build/, /DerivedData/, /scratch/, /docs/, /.claude/, /.claude-plugin/ Phase 1: Map Foundation Models Surface Step 1: Identify Imports and Deployment Target Step 2: Identify Sessions and Their Owners Step 3: Identify Availability and Lifecycle Surface Step 4: Identify @Generable / @Guide / Tool Surface Step 5: Identify Inference and Error-Handling Surface Search BOTH error spellings. The 27 SDK deprecated LanguageModelSession.GenerationError in favor of LanguageModelError, and split assetsUnavailable / concurrentRequests / decodingFailure out into SystemLanguageModel.Error, LanguageModelSession.Error, and GeneratedContent.ParsingError. A project written against the 27 API contains none of the old identifiers — grepping only for those reports a modern codebase as having no error handling at all, which is the opposite of the truth. See axiom-ai (skills/foundation-models-ref.md) for the full migration table. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills charleswiltgen/axiom-audit-foundation-models