WeatherXM FACT
WeatherXM AG v1.0.3
Weather forecast benchmarks
From the developer
Declared capabilities
- Read published historical local forecast accuracy
- Inspect country-level published cell-win summaries
- Compare global model error curves with cohort caveats
Declared limitations
- Do not trigger for ecommerce order refunds or billing changes.
- Do not trigger for calendar scheduling or email sending.
- Do not trigger for smart-home thermostat or IoT device mutations.
Not specified in the available declarations: pricing & account requirements.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 11, 2026. Package observed Nov 11, 2026.
Description
From the marketplace listing
WeatherXM FACT compares published historical forecast accuracy across 45 numerical and AI weather models using the WeatherXM station archive. Query local historical benchmark results, country cell-win summaries, global model error curves and historical publication coverage. Outputs include provenance, missing-data and cohort limitations. This is not a live forecast, a guarantee of future accuracy, or a live station inventory. The service requires no account. Coarse H3 query-demand telemetry is stored for coverage planning; see the privacy policy.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 10, 2026. Last seen Nov 11, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Analyze US natural gas weather demand with GEFS and ECMWF EPS degree-day forecasts and model-run comparisons.
Shared terms: forecast, weather, demand, historical
-
Transform forecasts into personalized outlooks and interactive apps, with our suite of agentic weather tools. Share what you're planning ...
Shared terms: forecast, global, planning, weather
-
Public air-quality data, historical PM2.5, city rankings and weather from Atmy.
Shared terms: weather, country, coverage, forecast
-
Unofficial Taiwan township forecasts with near-term hourly detail or a seven-day day/night outlook, in-district stations and backend shor...
Shared terms: weather, coverage, forecast, guarantee
-
Arrival-time weather forecasts along a drive, published highway forecasts, and links to continue planning in Windshield Weather.
Shared terms: weather, forecast, historical, planning
Keywords
Files & skills
File archives
Skill instructions
weatherxm-fact1.76 KB
--- name: weatherxm-fact description: Read published WeatherXM FACT historical forecast accuracy, country cell-win summaries, global model error curves, and historical station-publication coverage. Use for explicit forecast-model benchmark questions, not live weather or current station inventory. --- # WeatherXM FACT Use only the four tools actually exposed by weatherxm-fact: - get_best_forecast_model: query a location or station_or_report_id and published historical model performance. - check_ground_truth_coverage: query historical archive publication coverage; it does not establish current station presence or absence. - get_fact_leaderboard: query global error metrics or country cell-win counts using country, variable, lead_day and exclude_commissioned. Country cell wins are not national matched-sample MAE rankings. - get_model_head_to_head: pass a models array (for example IFS025 and GFS05) and variable to compare global source-specific lead-day curves. No model_a, model_b or country parameters are supported by this tool. Variables: temperature, wind_speed, precipitation, humidity. Where supported, lead_day is a string: all or 0 through 7. Use current tool schemas. Do not invent a tool. Only send task-specific benchmark inputs. Do not ask for the user's precise personal location, account credentials or chat history. Prefer an existing public station/report identifier when supplied. Coarse H3 query metadata is retained for demand analytics; do not claim the service stores no query data. Preserve provenance, data-as-of dates, missing-result states, commissioned-model and source-cohort caveats. Separate reference cells from requested sites. Never treat historical results as live forecasts, guaranteed future skill, or proof that buying a station improves accuracy.
Release notes
Updates privacy policy URL and disclosures for MCP tool inputs, outputs, H3 quantization, recipients, retention timelines, and user controls.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- WeatherXM AG
- Keywords
- See keywords
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Read published historical local forecast accuracy
- Inspect country-level published cell-win summaries
- Compare global model error curves with cohort caveats
- Check historical ground-truth publication coverage
Package observed Nov 11, 2026.
Technical details
- First seen
- Nov 10, 2026 · 00:00 UTC
- Last seen
- Nov 11, 2026 · 18:00 UTC
- Collection status
- Collected
plugin_asdk_app_6aec5b8ca5148191ba7fa1fc63baf563
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.