Use when implementing location services, maps, geofencing, or debugging location/MapKit issues. Covers Core Location, CLMonitor, MapKit, annotations, directions.

Use when integrating ANY iOS system feature - Siri, Shortcuts, widgets, IAP, localization, privacy, alarms, calendar, reminders, contacts, background tasks, push notifications, timers. Covers App Intents, WidgetKit, StoreKit, EventKit, Contacts.

Use when working with HealthKit, WorkoutKit, health data, workouts, or fitness features on iOS or watchOS. Covers permissions, queries, background delivery, custom workouts, multidevice coordination.

Use when working with ANY GPU rendering, Metal, OpenGL migration, shaders, 3D content, RealityKit, AR, USD/USDZ files, or display performance. Covers Metal migration, shader conversion, RealityKit ECS, RealityView, USDKit, ProMotion.

Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit, or adding touch controls or game controller support. Covers scene graphs, ECS, physics, actions, game loops, rendering, TouchController, GCController.

Use when making design decisions, implementing HIG patterns, Liquid Glass, SF Symbols, typography, or structuring app entry points and authentication flows.

Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization. Covers SwiftData, Core Data, GRDB, SQLite, CloudKit sync, file storage, Codable, migrations.

Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.

Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code. Covers build failures, compilation errors, dependency conflicts, simulator problems, environment-first diagnostics.

Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation. Covers Liquid Glass, Swift 6.2 concurrency, Foundation Models, SwiftData, StoreKit, 32 Swift compiler diagnostics.

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.

Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.

Registers node major version vanity URL in the sibling vanity repo

Generates CHANGELOG.md entries for upgrade versions found in upgrades/software/ by parsing init.go and upgrade.go

Set up development environment by loading direnv. Must be run before any make targets (tests, builds, linting).

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Reference for OrangeHRM's service layer — the `*/Service/<Name>Service.php` classes that sit between Endpoints/Controllers and DAOs and hold business logic, the `*ServiceTrait` DI access pattern, the lazy-getter convention for composing services, where to register services in `PluginConfigurationInterface::initialize()`, and what belongs in a service vs in a DAO vs on an entity Decorator. Use whenever the user is adding a service method, deciding where business logic should live, composing one service from another, or asking "is there already a service for X?" Companion to `daos` (the layer services call into), `rest-endpoints` (the layer that calls services), `entities` (the Decorator alternative for entity-bound logic).

Reference for OrangeHRM's task scheduling — the `orangehrm:run-schedule` command that operators run from system cron (every minute), the `SchedulerConfigurationInterface` that plugins implement to register tasks at framework boot, the `Schedule` / `Task` / `CommandInfo` value objects (Task extends `Crunz\Event`, so all Crunz fluent scheduling methods like `->cron()`, `->everyMinute()`, `->hourly()`, `->daily()`, `->weekdays()`, `->between()`, etc. are available), and the `TaskSchedulerLog` entity that records every task execution. Use whenever the user is adding a recurring background task, wiring up cron, debugging a job that should have run but didn't, or asking about setting up the host-level cron entry. Companion to `console-commands` (scheduled jobs are console commands underneath), `events` (the same plugin-config-implements-interface pattern), `mail` (a common scheduled task is draining queued emails on hosts where it can't happen via TERMINATE).

Reference for OrangeHRM's REST API v2 input validation — `ParamRule`, `ParamRuleCollection`, `Rule`, the `Rules::*` constant catalog (OrangeHRM custom rules + Respect/Validation rules), the `ValidationDecorator` for required/not-required wrapping, composite rules (ALL_OF / ANY_OF / ONE_OF / NONE_OF), and writing custom rule classes. Use whenever the user is writing or editing a `getValidationRuleFor*()` method on an Endpoint, debugging a 422 "Invalid parameter" response, asking which rule exists for a check, writing a new `Rules\Foo` class, or wondering why a required-looking field passes empty-string. Companion to the `rest-endpoints` skill which covers the Endpoint dispatch flow.

Reference for shaping OrangeHRM REST API v2 responses — the `Normalizable` + `ModelTrait` contract, writing a Model class that maps a Doctrine entity to a JSON object, the `filter` array (getter chain — supports nested-getter sequences for related entities), the `attributeNames` array (output JSON keys), `EndpointResourceResult` vs `EndpointCollectionResult`, the `ParameterBag` meta envelope, generic non-entity models (`ArrayModel`, `ArrayCollectionModel`), and the `MODEL_MAP` pattern for `?model=default|detailed` variants. Use whenever the user is writing or editing a Model class, picking which `EndpointResult` to return, debugging "why is field X missing/null in the JSON response", adding a detailed-vs-default model variant, or returning an ad-hoc payload that doesn't come from an entity. Companion to `rest-endpoints` (the dispatch spine) and `rest-openapi` (Model classes carry `@OA\Schema`).