rhiza-research/weather-skills
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
AI skills
概要
⚠️ These skills are an early experiment in tool composition for weather/climate data pipelines. Interfaces, dataset schema, and skill boundaries may change without notice. Fetchers hit real APIs and require credentials; middle- pipeline skills have only been smoke-tested on small synthetic data. Do not use in any automated workflow you rely on, and do not assume outputs are scientifically validated. Expect breakage. Small tools an AI agent can run to fetch weather data and transform it. Each skill is a command-line script. They share one Zarr file format so outputs of one skill can feed into the next — see STANDARD_DATASET.md. Built as Agent Skills by Rhiza Research. Prefer dynamical-fetch when the dynamical.org catalog has the dataset (GFS, GEFS, ECMWF IFS-ENS, AIFS, Google WeatherNext 2, ICON-EU, analyses, IMERG, CHIRPS). Use a credentialed or source-specific fetcher only when it does not. Capabilities the agent uses alongside pipelines; none of them produces a dataset output.
README
以下は原文 README の抜粋です。原文を見る。
Weather Skills
⚠️ Under active development — not production ready.
These skills are an early experiment in tool composition for weather/climate data pipelines. Interfaces, dataset schema, and skill boundaries may change without notice. Fetchers hit real APIs and require credentials; middle- pipeline skills have only been smoke-tested on small synthetic data. Do not use in any automated workflow you rely on, and do not assume outputs are scientifically validated. Expect breakage.
Small tools an AI agent can run to fetch weather data and transform it. Each
skill is a command-line script. They share one Zarr file format so outputs of
one skill can feed into the next — see
STANDARD_DATASET.md.
Built as Agent Skills by Rhiza Research.
Skills
Fetchers (ingress — source-specific)
Prefer dynamical-fetch when the dynamical.org catalog has the dataset
(GFS, GEFS, ECMWF IFS-ENS, AIFS, Google WeatherNext 2, ICON-EU, analyses,
IMERG, CHIRPS). Use a
credentialed or source-specific fetcher only when it does not.
| Skill | What it does |
|---|---|
dynamical-fetch |
Preferred when the catalog has it. dynamical.org open catalog (GFS, GEFS, ECMWF IFS-ENS 15-day and 46-day, AIFS, Google WeatherNext 2, ICON-EU, MRMS, analyses, IMERG, CHIRPS) via --dataset, credential-free → Zarr. Forecasts: one init (--date) or a range of inits (repeatable --start-time/--end-time). Default IMERG source: nasa-imerg-analysis-late / nasa-imerg-analysis-early. CHIRPS products: ucsb-chc-chirps-analysis-final / ucsb-chc-chirps-analysis-preliminary. |
ecmwf-fetch |
ECDS fallback for ECMWF S2S / ER (pre-2026, ocean, unmapped fields). Prefer dynamical-fetch --dataset ecmwf-ifs-ens-forecast-46-day-daily-1-5-degree for 2026+ catalog fields. |
chirps-fetch |
Default CHIRPS source: dynamical.org final + prelim fallback → precip Zarr |
imerg-fetch |
Earthdata daily IMERG Final (GPM_3IMERGDF) → Zarr. All IMERG Late/Early comes from dynamical-fetch. |
clim-fetch |
Climatology (mean + std) for a --dataset (imerg_final, era5, chirps, ecmwf_ifs, oisst, …), at a selected --prediction-timedelta lead and --window (days; correctly rolled up, centered, with circular padding if not pre-mirrored), expanded to a --start-time/--end-time window → Zarr. OISST SST is --dataset oisst --variable sst. |
tahmo-fetch |
TAHMO station observations (daily-aggregated) → Zarr |
3dpaws-fetch |
3D-PAWS station observations from a CHORDS portal (default: FEWS NET Kenya; daily precip, temperature, humidity, pressure, wind) → station Zarr. Requires credentials. |
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add rhiza-research/weather-skills