skill · Global

weather-skill

Platform-agnostic weather skill for AI agents

Feature or claim this listing

Represent weather-skill? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Data offered docs-verified: current weather · multi-day forecast (3 to 16 days, depending on provider) · air quality index (AQHI, PSI or AQI, from HKO, SG NEA and OpenWeatherMap)
Coverage docs-verified: Global via Open-Meteo fallback and OpenWeatherMap; dedicated national providers for Hong Kong, Singapore, Japan, Taiwan, UK, Australia, New Zealand, USA, Indonesia, Germany, South Korea and Thailand
Formats docs-verified: JSON · CLI text · Telegram MarkdownV2 · WhatsApp formatting
Access docs-verified: Open source under MIT licence. 9 of 14 providers need no API key. The other 5 (CWA, UK Met Office, KMA, TMD, OpenWeatherMap) need a provider key from the sign-up links in the docs. Telegram delivery also needs a bot token.

Use cases llm-inferred: Weather context for UK site visits and fieldwork planning via the UK Met Office provider (requires METOFFICE_API_KEY) · Multi-day forecast briefs for project teams, sent as Telegram or WhatsApp-formatted messages · Structured JSON weather pulls piped into an agent or script for site-log or reporting workflows · Air quality context (AQHI, PSI or AQI) for sites in Hong Kong, Singapore or globally via OpenWeatherMap
Audience llm-inferred: environmental consultants · civils and geotechnical engineers · project managers · AI agent developers

Constraints docs-verified: Default location is Hong Kong, so UK users must pass a location explicitly · Locations with no dedicated provider (for example India, Canada, China) fall back to global providers · MetService (New Zealand) returns current weather only, with no forecast · Air quality is available only from HKO, SG NEA and OpenWeatherMap; other providers have none · No hydrological, river-gauge, rainfall-radar or ground-condition data is documented · No historical data, spatial resolution or update frequency is documented · Standalone binaries exist only for Linux x86-64 and macOS arm64; the Bun package is source-install only, with no npm package

Licence: MIT
Authentication: API key via env: CWA_API_KEY, KMA_SERVICE_KEY, METOFFICE_API_KEY, OPENWEATHERMAP_API_KEY, TELEGRAM_BOT_TOKEN, TMD_API_TOKEN (auto-extracted from README)
GitHub stars: 1
Last commit: 05/10/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: pypi:weather-skill
Verification: Not independently verified

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 16/10/2026 · daily-2026-10-15 (github-search)