Weatherkit logo

Weatherkit

CommunityPopular
dpearson2699
weatherkit

Fetch WeatherKit current, minute, hourly, and daily forecasts; weather alerts; iOS 18+ changes, historical comparisons, summaries, and statistics; and required Apple Weather attribution. Use when integrating weather data, showing forecasts or alerts, caching WeatherKit responses, displaying attribution, or reviewing WeatherKit query limits in iOS apps.

Overview

Publisherdpearson2699
Repositoryswift-ios-skills
Skill nameweatherkit
Stars
1.2K
Forks
61
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dpearson2699 on GitHub. Read the source before you install it.

Installation

Install the Weatherkit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/weatherkit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills.git /tmp/swift-ios-skills
mkdir -p .claude/skills
cp -r /tmp/swift-ios-skills/skills/weatherkit .claude/skills/weatherkit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Weatherkit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Weatherkit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Weatherkit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

WeatherKit

Fetch current conditions, hourly and daily forecasts, weather alerts, and historical statistics using WeatherService. Display required Apple Weather attribution.

Contents

Setup

Project Configuration

  1. Enable the WeatherKit capability in Xcode (adds the entitlement)
  2. Enable WeatherKit for your App ID in the Apple Developer portal
  3. Add NSLocationWhenInUseUsageDescription to Info.plist if using device location
  4. WeatherKit requires an active Apple Developer Program membership

Import

swift
import WeatherKit
import CoreLocation

Creating the Service

Use the shared singleton or create an instance. WeatherService conforms to Sendable; keep app cache and UI state isolated separately.

swift
let weatherService = WeatherService.shared
// or
let weatherService = WeatherService()

Fetching Current Weather

Fetch current conditions for a location. Returns a Weather object with all available datasets.

WeatherKit temperatures are Measurement<UnitTemperature> values; display them with .formatted() so units and number formatting follow the user's locale.

swift
func fetchCurrentWeather(for location: CLLocation) async throws -> CurrentWeather {
    let weather = try await weatherService.weather(for: location)
    return weather.currentWeather
}

// Using the result
func displayCurrent(_ current: CurrentWeather) {
    let temp = current.temperature  // Measurement<UnitTemperature>
    let condition = current.condition  // WeatherCondition enum
    let symbol = current.symbolName  // SF Symbol name
    let humidity = current.humidity  // Double (0-1)
    let wind = current.wind  // Wind (speed, direction, gust)
    let uvIndex = current.uvIndex  // UVIndex

    print("\(condition): \(temp.formatted())")
}

Forecasts

Hourly Forecast

Returns 25 contiguous hours starting from the current hour by default.

swift
func fetchHourlyForecast(for location: CLLocation) async throws -> Forecast<HourWeather> {
    let weather = try await weatherService.weather(for: location)
    return weather.hourlyForecast
}

// Iterate hours
for hour in hourlyForecast {
    print("\(hour.date): \(hour.temperature.formatted()), \(hour.condition)")
}

Daily Forecast

Returns 10 contiguous days starting from the current day by default.

swift
func fetchDailyForecast(for location: CLLocation) async throws -> Forecast<DayWeather> {
    let weather = try await weatherService.weather(for: location)
    return weather.dailyForecast
}

// Iterate days
for day in dailyForecast {
    print("\(day.date): \(day.lowTemperature.formatted()) - \(day.highTemperature.formatted())")
    print("  Condition: \(day.condition), Precipitation: \(day.precipitationChance)")
}

Custom Date Range

Request forecasts for specific date ranges using WeatherQuery.

Daily and hourly date-range queries use an inclusive startDate and exclusive endDate. They can include historical data from August 1, 2021. Forecasts are available up to 10 days in the future; each request returns at most 10 daily forecast days or about 240 hourly forecast hours.

swift
func fetchExtendedForecast(for location: CLLocation) async throws -> Forecast<DayWeather> {
    let startDate = Date.now
    let endDate = Calendar.current.date(byAdding: .day, value: 10, to: startDate)!

    let forecast = try await weatherService.weather(
        for: location,
        including: .daily(startDate: startDate, endDate: endDate)
    )
    return forecast
}

For tomorrow-specific guidance, request the local tomorrow day interval rather than using minute forecasts:

swift
func fetchTomorrowForecast(for location: CLLocation) async throws -> Forecast<DayWeather> {
    let calendar = Calendar.current
    let tomorrow = calendar.startOfDay(
        for: calendar.date(byAdding: .day, value: 1, to: .now)!
    )
    let dayAfterTomorrow = calendar.date(byAdding: .day, value: 1, to: tomorrow)!

    return try await weatherService.weather(
        for: location,
        including: .daily(startDate: tomorrow, endDate: dayAfterTomorrow)
    )
}

Weather Alerts

Fetch active weather alerts for a location. Alerts include severity, summary, and affected regions.

swift
func fetchAlerts(for location: CLLocation) async throws -> [WeatherAlert]? {
    let weather = try await weatherService.weather(for: location)
    return weather.weatherAlerts
}

// Process alerts
if let alerts = weatherAlerts {
    for alert in alerts {
        print("Alert: \(alert.summary)")
        print("Severity: \(alert.severity)")
        print("Region: \(alert.region ?? "Unknown region")")
        print("Details: \(alert.detailsURL)") // Non-optional and required for attribution
    }
}

For alert dashboards, name WeatherAvailability explicitly when discussing support checks: it exposes alertAvailability and minuteAvailability only, not a broad availability matrix for current, hourly, or daily weather.

Selective Queries

Fetch only the datasets you need to minimize API usage and response size. Each WeatherQuery type maps to one dataset.

Single Dataset

swift
let current = try await weatherService.weather(
    for: location,
    including: .current
)
// current is CurrentWeather

Multiple Datasets

swift
let (current, hourly, daily) = try await weatherService.weather(
    for: location,
    including: .current, .hourly, .daily
)
// current: CurrentWeather, hourly: Forecast<HourWeather>, daily: Forecast<DayWeather>

Minute Forecast

Available in limited regions. Returns precipitation forecasts at minute granularity for the next hour.

swift
let minuteForecast = try await weatherService.weather(
    for: location,
    including: .minute
)
// minuteForecast: Forecast<MinuteWeather>?  (nil if unavailable)

Available Query Types

QueryReturn TypeDescription
.currentCurrentWeatherCurrent observed conditions
.hourlyForecast<HourWeather>25 hours from current hour
.dailyForecast<DayWeather>10 days from today
.minuteForecast<MinuteWeather>?Next-hour precipitation (limited regions)
.alerts[WeatherAlert]?Active weather alerts
.availabilityWeatherAvailabilityAlert and minute forecast availability only
.changesWeatherChanges?Significant upcoming weather changes (iOS 18+)
.historicalComparisonsHistoricalComparisons?Current weather compared to historical averages (iOS 18+)

Context Queries

For "unusual tomorrow" or "what is changing?" features on iOS 18+, request the optional .changes and .historicalComparisons results together: the first reports significant upcoming changes and the second provides historical context.

swift
let (changes, comparisons) = try await weatherService.weather(
    for: location,
    including: .changes, .historicalComparisons
)

Historical summaries and statistics use WeatherService methods rather than WeatherQuery. Load references/weatherkit-patterns.md for their tuple ordering, APIs, and statistics-specific properties.

Attribution

Apple requires apps using WeatherKit to display attribution. This is a legal requirement.

Fetching Attribution

swift
func fetchAttribution() async throws -> WeatherAttribution {
    return try await weatherService.attribution
}

Load references/weatherkit-patterns.md for the complete SwiftUI attribution view and cache integration.

Attribution Properties

PropertyUse
combinedMarkLightURLApple Weather mark for light backgrounds
combinedMarkDarkURLApple Weather mark for dark backgrounds
squareMarkURLSquare Apple Weather logo
legalPageURLURL to the legal attribution web page
legalAttributionTextText alternative when a web view is not feasible
serviceNameWeather data provider name

Availability

Check whether weather alerts or minute forecast data are available for a location. WeatherAvailability reports only alert and minute availability; other datasets, such as current weather, are expected to be supported for geographic locations.

swift
func checkAvailability(for location: CLLocation) async throws {
    let availability = try await weatherService.weather(
        for: location,
        including: .availability
    )

    // Check specific dataset availability
    if availability.alertAvailability == .available {
        // Safe to fetch alerts
    }

    if availability.minuteAvailability == .available {
        // Minute forecast available for this region
    }
}

Common Mistakes

DON'T: Ship without Apple Weather attribution

Display the appropriate Apple Weather mark and link legalPageURL wherever WeatherKit data appears; use legalAttributionText only when the legal page cannot be shown.

DON'T: Fetch all datasets when you only need current conditions

Each dataset query counts against your API quota. Use the selective query shown in Selective Queries and fetch only what the UI displays.

DON'T: Ignore minute forecast unavailability

Minute forecasts are optional in unsupported regions. Check availability and handle the nil result instead of force-unwrapping it.

DON'T: Forget the WeatherKit entitlement

Without the capability enabled, WeatherService calls throw at runtime.

swift
// WRONG: No WeatherKit capability configured
let weather = try await weatherService.weather(for: location) // Throws

// CORRECT: Enable WeatherKit in Xcode Signing & Capabilities
// and in the Apple Developer portal for your App ID

DON'T: Make repeated requests without caching

WeatherKit models include metadata.expirationDate. Cache responses until that expiration instead of inventing a fixed interval or fetching on every view appearance. Let a model or cache own loadIfNeeded; the complete actor pattern is in references/weatherkit-patterns.md.

Review Checklist

  • WeatherKit capability enabled in Xcode and Apple Developer portal
  • Active Apple Developer Program membership (required for WeatherKit)
  • Apple Weather attribution displayed wherever weather data appears
  • Attribution mark uses correct color scheme variant (light/dark)
  • Legal attribution page linked or legalAttributionText displayed
  • Only needed WeatherQuery datasets fetched (not full weather(for:) when unnecessary)
  • Minute forecast handled as optional (nil in unsupported regions)
  • Weather alerts checked for nil before iteration
  • Alert detail links use non-optional detailsURL; optional region is nil-safe
  • Responses cached until each model's metadata.expirationDate
  • WeatherAvailability used for alert/minute availability, not as a broad support matrix
  • Location permission requested before passing CLLocation to service
  • Temperature and measurements formatted with Measurement.formatted() for locale

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Weatherkit AI skill do?

Fetch WeatherKit current, minute, hourly, and daily forecasts; weather alerts; iOS 18+ changes, historical comparisons, summaries, and statistics; and required Apple Weather attribution. Use when integrating weather data, showing forecasts or alerts, caching WeatherKit responses, displaying attribution, or reviewing WeatherKit query limits in iOS apps.

Why use Weatherkit on TypingMind?

Because you install it once and use it with any model. Weatherkit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Weatherkit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/weatherkit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Weatherkit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Weatherkit?

As many as you like. As long as a model supports skills, you can use Weatherkit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Weatherkit AI skill free?

It is published on GitHub by dpearson2699. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇