Weather Skill

Provides current weather and forecasts for any location using two free APIs:

• Nominatim (OpenStreetMap) for geocoding locations → scripts/geocode.py
• Open-Meteo for weather data → scripts/fetch_weather.py

Workflow

1. Understand the user’s request. Extract the location, time range, and whether they’re planning travel. See examples below.
2. Geocode the location by running scripts/geocode.py "<location>". It returns JSON with display_name, lat, lon, and an ambiguous flag. If ambiguous, ask the user to clarify.
3. Fetch weather by running scripts/fetch_weather.py with the lat/lon and appropriate flags. See script usage below.
4. Respond to the user with a clear summary. See example outputs below.
5. If travel intent is detected, also read references/clothing_guide.md and include relevant clothing advice.

Scripts

Geocode: scripts/geocode.py

Converts a location string to coordinates.

python scripts/geocode.py "Tokyo"
python scripts/geocode.py "King Abdullah Financial District, Riyadh"
python scripts/geocode.py "Times Square, New York"

Returns JSON:

{
  "display_name": "Tokyo, Japan",
  "lat": 35.6764,
  "lon": 139.6500,
  "importance": 0.82,
  "ambiguous": false
}

If ambiguous is true, an alternatives list is included — ask the user which they meant.

Weather: scripts/fetch_weather.py

Fetches weather data for given coordinates.

# Current conditions only
python scripts/fetch_weather.py --lat 35.6764 --lon 139.65 --resolution current

# Hourly forecast (good for today, tomorrow, next 12 hours, specific day)
python scripts/fetch_weather.py --lat 35.6764 --lon 139.65 --resolution hourly

# Daily forecast (good for multi-day ranges, next week, etc.)
python scripts/fetch_weather.py --lat 35.6764 --lon 139.65 --resolution daily

# Custom timezone (default is "auto" which uses the location's timezone)
python scripts/fetch_weather.py --lat 35.6764 --lon 139.65 --resolution hourly --timezone Asia/Tokyo

# Include historical data when user asks about past weather
python scripts/fetch_weather.py --lat 35.6764 --lon 139.65 --resolution daily --past-days 7

Returns JSON with meta, current, hourly, and/or daily sections depending on resolution.

Example JSON response (--resolution current):

{
  "meta": {
    "lat": 35.6764,
    "lon": 139.65,
    "timezone": "Asia/Tokyo",
    "resolution": "current",
    "forecast_days": 16,
    "past_days": 0
  },
  "current": {
    "time": "2026-02-25T14:00",
    "temperature_c": 12.3,
    "apparent_temperature_c": 10.8,
    "weather_code": 1,
    "weather_description": "Mainly clear",
    "wind_speed_kmh": 14.2,
    "humidity_pct": 48,
    "precipitation_mm": 0.0
  },
  "hourly": null,
  "daily": null
}

The script always requests forecast_days=16 (max forecast horizon). Use --past-days only for past weather requests (0..92).

How to Interpret User Requests

The agent should interpret the user’s natural language to determine three things:

1. Location

Extract the place name from the query. Examples:

• “Weather in Jeddah now” → "Jeddah"
• “Forecast for London this weekend” → "London"
• “I’m going to Tokyo next week” → "Tokyo"
• “How windy will it be in AlUla on Friday?” → "AlUla"

If no location is mentioned, ask the user.

2. Time Range, Resolution, and Past Weather

The user may specify dates in various formats (MM/DD, DD/MM, “May 1st”, “1 March”, etc.) — interpret based on context and filter the returned timeline accordingly. Use the current year unless another year is stated or implied.

Use daily for ranges > 3 days, hourly for shorter windows, current for right-now queries (but still include hourly for context).

Default (no time specified): current conditions + next 24 hours hourly.

Remember: Forecast is fixed to 16 days. For past requests, use past_days (0..92).

3. Travel Intent

Detect if the user is planning to go somewhere. Look for keywords like: pack, wear, travel, visiting, going to, headed to, trip, vacation, holiday, outing, flight, should I bring

If travel intent is detected → also include clothing guidance (see below).

Example Outputs

Example 1: Simple current weather

User: “What’s the weather in Jeddah now?”

Response:

Weather in Jeddah, Saudi Arabia

Right now it’s Clear sky with a temperature of 28°C (feels like 30°C). Wind is light at 12 km/h from the north, and humidity is at 45%. No precipitation expected.

Next few hours:

• 3 PM: 29°C, Clear sky, 0% rain
• 4 PM: 28°C, Partly cloudy, 0% rain
• 5 PM: 26°C, Clear sky, 0% rain (and so on…)

Example 2: Weekend forecast

User: “Forecast for London this weekend”

Response:

Weekend Forecast for London, UK

Saturday, Mar 1: Highs of 11°C, lows of 5°C. Moderate rain expected (70% probability, ~4mm). Wind up to 25 km/h.

Sunday, Mar 2: Highs of 13°C, lows of 6°C. Partly cloudy, 20% rain chance. Lighter wind at 15 km/h.

Overall: A wet Saturday clearing into a drier Sunday. Bring an umbrella for Saturday.

Example 3: Travel planning with clothing advice

User: “I’m going to Tokyo next week — what should I pack?”

Response:

Tokyo, Japan — Next Week Forecast (Mar 3–9)

Day	High	Low	Conditions	Rain	Wind
Mon	12°C	4°C	Partly cloudy	10%	15 km/h
Tue	10°C	3°C	Slight rain	65%	20 km/h
…	…	…	…	…	…

What to Wear: Expect cold conditions (lows near 3°C) with rain mid-week. Pack:

• Warm layers: fleece or wool sweater + insulated jacket
• Waterproof jacket and umbrella for Tuesday/Wednesday
• Closed-toe waterproof shoes
• Scarf and light gloves for mornings/evenings

See: clothing_guide.md — sections: cold, rainy

Example 4: Specific condition query

User: “How windy will it be in AlUla on Friday?”

Response:

Wind Forecast for AlUla, Saudi Arabia — Friday, Feb 28

Wind speeds will peak at 35 km/h in the early afternoon, settling to around 15 km/h by evening. Morning winds are lighter at ~10 km/h.

⚠️ Moderately windy conditions expected midday — secure loose items and consider a windbreaker if you’ll be outdoors.

Warnings

Include warnings when conditions are notable:

• Extreme heat: temp ≥ 40°C
• Extreme cold: temp ≤ -10°C
• Strong wind: ≥ 50 km/h
• Heavy rain: ≥ 20mm precipitation

Clothing Guidance

When travel intent is detected, read references/clothing_guide.md and include relevant advice in the response.

Error Handling

• Location not found: Ask the user to be more specific (add city, country).
• Ambiguous location: Present the alternatives and ask which one.
• API failure / network blocked: Scripts return a JSON error envelope instead of a traceback:

  {
    "error": {
      "code": "NETWORK_UNAVAILABLE",
      "message": "Unable to reach remote weather service.",
      "details": "URLError: ...",
      "retryable": true,
      "hint": "Enable outbound network access or rerun with elevated permissions."
    }
  }
  

• Error codes:
  • INVALID_INPUT: bad user input (invalid past_days, missing location, no results).
  • NETWORK_UNAVAILABLE: DNS/connectivity/timeouts to upstream weather APIs.
  • UPSTREAM_API_ERROR: upstream HTTP/API response issues.
• Exit codes:
  • 0: success.
  • 1: usage or input validation failures.
  • 2: network/upstream API failures.
• Operational guidance: If network is blocked in a sandbox, request elevated permissions or run scripts from an environment with outbound internet access.
• Beyond forecast horizon: Inform them of the 16-day limit, return what’s available.
• No time specified: Default to current + next 24 hours.