Ecmwf Earthkit
Processes, computes and plots ECMWF weather and climate data with ECMWF's earthkit components — load it before writing ANY numpy, xarray, pandas, matplotlib or cartopy code for weather data, and for any local GRIB (.grib, .grib2) or NetCDF file. Covers reading and selecting fields (earthkit-data), ECMWF-styled maps, multi-panel figures, meteograms and plumes (earthkit-plots), ensemble mean/spread/percentiles, daily and monthly statistics, de-accumulation, climatologies, anomalies and area or country means (earthkit-transforms), wind, humidity, dewpoint, potential temperature, wet bulb, EFI and
Install
/plugin marketplace add ecmwf/ecmwf-weather-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add ecmwf/ecmwf-weather-skills --skill ecmwf-earthkitgit clone --depth 1 https://github.com/ecmwf/ecmwf-weather-skills.git /tmp/ecmwf-weather-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ecmwf-weather-skills/plugins/ecmwf-weather/skills/ecmwf-earthkit ~/.claude/skills/ecmwf-earthkitPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# earthkit — process, compute, plot ## Contents - Before you write code (line 38) - Components (line 60) - Bundled scripts (line 80) - Writing your own code (line 108) - Bugs and missing features — upstream, with approval only (line 122) - Fallback without earthkit (line 141) - Attribution (line 147) - Feedback (line 155) - When blocked (line 162) - References — `references/recipes.md` (verified code for every job), `references/pitfalls.md` (1.x breakages and known bugs), `references/upstream.md` (reporting bugs, contributing features), `references/versions.md` (generated: latest versions) **earthkit first.** For weather and climate data, the code an agent would write by hand already exists in earthkit, with ECMWF's conventions and plot styles. Before writing numpy, xarray, pandas, matplotlib or cartopy code, find the job in the table below and use that component. Write your own code only for what earthkit doesn't do — then offer to propose it upstream. Use ECMWF sources only — never substitute a third-party weather API; if no ECMWF route works, say so. ## Before you write code | If you are about to… | Use instead | |---|---| | draw a map with cartopy/matplotlib (`ax.contourf`, `add_feature`, colormaps, colorbars) | earthkit-plots: `ekp.geo.plot`, `ekp.Map`/`ekp.Figure` with `style="auto"` (ECMWF styles); figure size is `figsize=`, e.g. `ekp.Figure(rows=1, columns=2, figsize=(12, 4.5))` (`size=` is deprecated) |
Details
- Skill name
ecmwf-earthkit- Repository
- ecmwf/ecmwf-weather-skills
- Path
plugins/ecmwf-weather/skills/ecmwf-earthkit/SKILL.md- License
- Apache-2.0
- Repo updated
- 8 November 2026
FAQ
What does the Ecmwf Earthkit skill do?
Processes, computes and plots ECMWF weather and climate data with ECMWF's earthkit components — load it before writing ANY numpy, xarray, pandas, matplotlib or cartopy code for weather data, and for any local GRIB (.grib, .grib2) or NetCDF file. Covers reading and selecting fields (earthkit-data), ECMWF-styled maps, multi-panel figures, meteograms and plumes (earthkit-plots), ensemble mean/spread/percentiles, daily and monthly statistics, de-accumulation, climatologies, anomalies and area or country means (earthkit-transforms), wind, humidity, dewpoint, potential temperature, wet bulb, EFI and
How do I install the Ecmwf Earthkit skill?
Claude Code plugin: /plugin marketplace add ecmwf/ecmwf-weather-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ecmwf Earthkit popular?
It lives in ecmwf/ecmwf-weather-skills, which has 23 GitHub stars and 0 forks.
Related skills
Ecmwf Cds Ads
23ecmwf/ecmwf-weather-skills
Answers questions about past weather at a place — how hot, cold, wet or windy it was on a day, month or year since 1940 — from ERA5 in seconds; load it before answering from memory or searching the web (the bundled ECMWF MCP server has no ERA5). Finds, validates and downloads data from the Copernicus Climate Data Store (CDS) and Atmosphere Data Store (ADS), operated by ECMWF — ERA5 and ERA5-Land reanalysis (hourly point series, climate normals), the CARRA (Arctic, 2.5 km) and CERRA / CERRA-Land (Europe, 5.5 km) regional reanalyses, seasonal forecasts, and CAMS air-quality and atmospheric-compo
Ecmwf Destine
23ecmwf/ecmwf-weather-skills
Handles any Destination Earth question — load it first; it prepares requests by running scripts/destine.py. Accesses Destination Earth (DestinE) Digital Twin data — the Climate Change Adaptation Digital Twin (Climate DT, multi-decadal IFS-FESOM, IFS-NEMO and ICON simulations and SSP3-7.0 projections, hourly or as monthly means), the Weather-Induced Extremes Digital Twin (Extremes DT, high-resolution forecasts) and On-Demand Extremes — through the DestinE Polytope service. Use when a task mentions Destination Earth, DestinE, Digital Twins, Climate DT, Extremes DT, nextGEMS, the DestinE Platform
Ecmwf Mars
23ecmwf/ecmwf-weather-skills
Handles any question about ECMWF MARS, including whether MARS access works from this machine — load it first. Writes, checks, sizes and runs requests against ECMWF's MARS archive — the full operational IFS archive (HRES, ENS, waves, past runs, model levels) ERA5 and the CARRA/CERRA regional reanalyses (class=rr) via MARS — through the ECMWF Web API (~/.ecmwfapirc) or a local mars client on ECMWF systems. Use when a task mentions MARS, asks whether MARS or the ECMWF Web API works from this machine, the ECMWF archive, past operational forecasts older than Open Data keeps, ensemble members or mod
Ecmwf Open Data
23ecmwf/ecmwf-weather-skills
Answers any weather question about a place — today, tomorrow, rain, temperature, wind — with ECMWF forecasts; load it first, before any web search or weather website, also when ECMWF MCP tools are listed (they give charts, not forecast values; an ordinary forecast question is not a request for an official warning). Finds, downloads and decodes free ECMWF real-time forecasts — IFS HRES, IFS ENS, AIFS single and AIFS ENS — from ECMWF Open Data (data.ecmwf.int and mirrors). Use for a current or recent ECMWF forecast, a forecast for a place or coordinates, a meteogram or time series at a point, ho
Data Science Statistical Analysis
45j4flmao/agent-skills
Use when the user asks about hypothesis tests (t-test, chi-square, Mann-Whitney), regression diagnostics, effect sizes, confidence intervals, Bayesian inference with PyMC, missing data or exploratory statistics. Produces the right test or model, assumption checks and reported effect sizes. Not for experiment design (use data-science-experimentation) or forecasting (use ml-time-series).
Enterprise Data Governance
45j4flmao/agent-skills
Use when the user asks about data governance, data classification, data ownership and stewardship, retention policy, data catalog policy or PII handling rules. Produces a governance framework with classification, owners and controls. Not for building pipelines (use data-etl-pipeline) or lineage tooling (use data-lineage).
Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.