rusel95

Run skill benchmarks with discriminating-only assertions against evals.json for any model and any AI agent. Use when benchmarking a skill against a model not yet tested, running with_skill/without_skill eval pairs, producing benchmark-<model>.json, re-grading an existing run, adding Phase 2 model comparison results, reviewing results in the eval viewer, updating README benchmark tables, or cleanin

Use for iOS/macOS concurrency problems involving dispatch queues, locks, or thread safety. Triggers on: deadlocks (sync on main, nested sync, ABBA lock ordering), thread explosion from too many DispatchQueue.global() calls, data races flagged by Thread Sanitizer (TSan), DispatchGroup enter/leave imbalance, DispatchSource timer leaks, lock selection (NSLock vs OSAllocatedUnfairLock vs os_unfair_loc

Enterprise skill for iOS production error observability and logging (iOS 15+, Swift 5.5+). The trigger is OBSERVABILITY intent — the user wants errors captured and visible in production, not just handled. Use when: adding os.Logger or replacing print() with structured logging; setting up or integrating a crash SDK (Sentry, Crashlytics, PostHog); auditing error handling for silent failures (catch b

Use for any iOS security question — whether you're asking about a specific vulnerability, checking if a pattern is secure, or running a full audit. Triggers on: Keychain vs UserDefaults decisions, ATS/NSAllowsArbitraryLoads configuration, certificate pinning implementation, WebView security (UIWebView, WKWebView), hardcoded secrets or API keys, jailbreak/tamper detection, biometric authentication,

Use for hands-on UIKit MVVM questions: setting up Combine bindings between UIViewController and ViewModel (@Published + sink), extracting business logic from massive ViewControllers step by step, testing ViewModels with XCTestExpectation + Combine publishers, fixing [weak self] retain cycles in sink closures, migrating DispatchQueue/GCD completion handlers to Combine, or replacing reloadData() wit

Production-grade iOS accessibility skill covering VoiceOver, Dynamic Type, color contrast, motion, Switch Control, Voice Control, and WCAG 2.2 compliance for both SwiftUI and UIKit. This skill should be used when creating new iOS screens or views, reviewing existing iOS code for accessibility, adding VoiceOver support, fixing Dynamic Type issues, auditing WCAG compliance, implementing accessibilit

Production-grade iOS localization skill covering String Catalogs (.xcstrings), CLDR pluralization, SwiftUI/UIKit localization APIs, RTL layout, date/number/currency formatting, and enterprise patterns (modular apps, white-label, accessibility localization). This skill should be used when creating or editing localized iOS strings, working with .xcstrings or .strings files, implementing pluralizatio

Use for any Swift Concurrency question on Apple platforms. Triggers on: actor reentrancy (stale state after await), AsyncStream lifecycle (continuation.finish, onTermination), TaskGroup memory and task throttling (activeProcessorCount), Sendable conformance across actor boundaries (non-Sendable third-party types), SWIFT_STRICT_CONCURRENCY=complete error triage ('Sending X risks causing data races'

Use when working with VIPER architecture in iOS/UIKit apps. Triggers on: creating new VIPER modules (View/Interactor/Presenter/Entity/Router); fixing retain cycles between VIPER layers; removing UIKit imports from Presenters; refactoring massive ViewControllers into VIPER layers; migrating VIPER Views to SwiftUI via UIHostingController; handling navigation with VIPER Routers; moving business logic

Invoke any time a user is writing iOS/Swift tests or asking why tests behave a certain way — including XCTest versus Swift Testing (@Test/#expect) choices, async ViewModel tests with @Observable or @Published, snapshot testing across device sizes, mocking protocols for dependency injection, setUp/tearDown lifecycle issues, tests that fail on CI but pass locally, flaky async tests, testing VIPER/TC

Use this skill when working with SwiftUI ViewModels — creating, refactoring, or testing them. Triggers for: setting up a ViewModel for a SwiftUI screen, extracting logic from a View into a ViewModel, migrating from ObservableObject to @Observable, modeling async state (instead of separate Bool flags like isLoading/hasError), injecting dependencies into ViewModels, writing unit tests for @Observabl

Use for any question about The Composable Architecture (TCA) — defining reducers, managing state, handling navigation, writing tests, or working with dependencies. Essential when encountering TCA-specific types like @Reducer, @ObservableState, StackState, StackAction, @Presents, TestStore, @DependencyClient, Scope, or delegate actions. Also use when debugging TCA compiler errors, decomposing large