Yr Weather

Fetch weather forecasts from the Norwegian Meteorological Institute (MET) using the yr.no API. Use when the user asks for weather information, forecasts, tem...

Security Scan

The skill's code, instructions, and requirements are consistent with a simple MET Norway (yr.no) weather client: it makes direct requests to api.met.no for forecasts, needs lat/lon, and demands no secrets or unusual privileges.

Purpose & Capability

Name/description claim (fetch forecasts from MET/yr.no) matches the included code: scripts/yr_service.py calls https://api.met.no/weatherapi/locationforecast/2.0/compact. No unrelated credentials, binaries, or services are requested.

Instruction Scope

SKILL.md instructs running the bundled Python CLIs (weather.py, tomorrow.py) with explicit lat/lon and points to tests that mock network calls. Instructions do not ask the agent to read unrelated files, environment variables, or transmit data to unexpected endpoints. Minor note: SKILL.md uses a {baseDir} placeholder which the agent must substitute when running commands.

Install Mechanism

The registry entry has no install spec (lowest-risk). The bundle includes Python source and a pyproject.toml; there is an optional README note showing how to pip-install the upstream GitHub repo (a standard GitHub URL). No downloads from obscure hosts, no extracted archives, and runtime behavior is limited to HTTP GET against MET's API.

Credentials

The skill requires no environment variables or credentials. It sets a benign User-Agent header and only performs unauthenticated calls to MET Norway. There are no requests for unrelated secrets or config paths.

Persistence & Privilege

The skill does not request persistent or elevated privileges (always: false). It does not modify other skills or system configuration and does not store credentials.

Assessment

This skill appears to do exactly what it says: call MET Norway's locationforecast API and format results. It does make outbound HTTP requests to api.met.no (no auth required) so ensure you are comfortable with that. The bundle includes the Python scripts and tests; no secrets are requested. If you plan to run pip install from the GitHub URL mentioned in the README/SKILL.md, review that external repo before installing system-wide. Also ensure the agent supplies lat/lon (there are no defaults) and substitutes the {baseDir} placeholder when invoking the provided CLI scripts.

Yr.no Weather

Get weather forecasts from MET Norway via yr.no API (free, no key).

Quick Start

# Current weather + forecast (requires lat/lon)
python3 {baseDir}/scripts/weather.py <lat> <lon> [altitude]

# Examples from common locations:
python3 {baseDir}/scripts/weather.py -33.9288 18.4174   # Cape Town
python3 {baseDir}/scripts/weather.py -33.8688 151.2093  # Sydney
python3 {baseDir}/scripts/weather.py 51.5074 -0.1278    # London

# Tomorrow's summary (requires lat/lon)
python3 {baseDir}/scripts/tomorrow.py <lat> <lon>

# Run tests
python3 -m unittest discover {baseDir}/tests

Tests

• Unit tests mock API calls (no network).
• Sample data in scripts/tests/data/.
• Run: cd {baseDir}/scripts && python3 ../tests/test_*.py

Common Locations

City	Lat	Lon
Cape Town	-33.9288	18.4174
Johannesburg	-26.2041	28.0473
Durban	-29.8587	31.0218
Sydney	-33.8688	151.2093
London	51.5074	-0.1278
New York	40.7128	-74.0060
Tokyo	35.6762	139.6503

Structure

scripts/
├── yr_service.py    # API calls (tested/mocked)
├── utils.py         # Emoji/symbol helpers
├── weather.py       # Current + forecast CLI
├── tomorrow.py      # Tomorrow summary CLI
└── tests/data/      # Sample JSON
tests/
├── test_weather.py
└── test_service.py

Standalone Repo

Install via pip: pip install git+https://github.com/brandoncrabpi/yr-weather.git

• yr-weather -33.9288 18.4174
• Tagged: v1.0.0

Usage Terms

• User-Agent required (included).
• Cache 10min+ per location.
• Credit: "Data from MET Norway".

Refactored for production: no defaults, tests, modular service.