Agent skill · vasilyu1983
software-ios-ai-engine
Design local AI engines for iOS. Use when wiring Apple Foundation Models, local classifiers, extraction, summarization, grounded answers, and cloud fallbacks.
What it needs
About 11k tokens when loaded.
What this skill does
Local AI Engine on iOS Use this skill when an iOS app should run useful AI behavior locally before spending cloud quota: Apple Foundation Models, deterministic local NLG, local retrieval stitching, local classifiers, extraction, summarization, tagging, rewrite helpers, and tool calls into app state. The common constraint is not "make chat smarter"; it is pick the right local engine, shape the data contract, gate capability correctly, and keep cloud as an explicit upgrade or fallback. A major scenario is a rich, per-user structured context bundle (chart, Human Design, planning cache, knowledge chunks, activity ratings, dream themes, mood/energy, etc.) that needs to produce a real answer without cloud quota. In that case, the fix is never "make the reject card nicer." The fix is adding a local Composer tier between intent routing and cloud fallback. This skill is for iOS product surfaces and local app-engine design. For pure retrieval/chunking/grounding strategy upstream of the local engine, route to ai-rag. For model serving/quantization tradeoffs beyond Apple platform APIs, route to ai-llm-inference. For evaluation of generated or extracted output, route to ai-evals-observer. Quick Reference Local Engine Patterns Pattern Local engine Best for Fallback --- --- --- --- Structured generation Apple Foundation Models + @Generable Short prose, extraction, classification, tagging, typed transformations Deterministic local logic or cloud opt-in Deterministic NLG Sentence bank / templates / rules Auditable answers, safety copy, older devices, per-locale consistency Retrieval stitch or cloud opt-in Retrieval stitch Local top-k chunks + wrappers Grounded explanations from existing knowledge chunks Sentence bank or cloud opt-in Local classifier Regex, NaturalLanguage, embeddings, FM enum output Routing, intent, entity extraction, safety boundaries Conservative default route Tool-backed local model FM tool calling into app state Model decides when it needs app data Pre-fetch com …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills vasilyu1983/software-ios-ai-engine