← Back to Skills Marketplace
Weather Ensemble Forecast
by
Lucasnocodo
· GitHub ↗
· v1.0.0
· MIT-0
294
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install weather-ensemble-forecast
Description
Multi-model ensemble weather forecasts comparing GFS, ECMWF, JMA, GEM, ICON, ARPEGE, GraphCast and more. Get high temperature predictions from up to 9 indepe...
Usage Guidance
This skill is coherent and small, but it depends entirely on a third‑party API server (default: https://polymarket-scanner.fly.dev). That server will see requests (city/date) and your IP, and if you set WEATHER_ENSEMBLE_API_KEY it will receive that key. If you are uncomfortable trusting that host, do not set the API key and/or set WEATHER_ENSEMBLE_HOST to a self-hosted or audited endpoint. Before installing, you may want to: (1) verify the polymarket-scanner.fly.dev service and its privacy policy; (2) run the included scripts locally to inspect responses; and (3) avoid storing unrelated secrets in environment variables the skill might read.
Capability Analysis
Type: OpenClaw Skill
Name: weather-ensemble-forecast
Version: 1.0.0
The weather-ensemble-forecast skill provides multi-model weather predictions by querying a dedicated API (polymarket-scanner.fly.dev). The provided Bash scripts (forecast.sh and cities.sh) perform standard API requests using curl and parse results with jq, including basic input sanitization to prevent shell injection. No evidence of data exfiltration, unauthorized command execution, or malicious prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match behavior: scripts call a weather-ensemble API, return per-model temperatures, compute ensemble stats server-side. Required binaries (curl, jq) are appropriate. The only external dependency is the listed Weather Ensemble API server.
Instruction Scope
SKILL.md and scripts instruct running two shell scripts that only call the configured HOST endpoint and parse JSON. They do not access arbitrary files, other env vars, or make unrelated network calls. Note: the skill relies entirely on the remote server (default polymarket-scanner.fly.dev) to aggregate models and cross-validate with NWS; the client scripts do not contact NWS directly.
Install Mechanism
There is no install spec and only two small shell scripts; nothing is downloaded or written to disk by an installer. This is low-risk and proportional.
Credentials
No required credentials. Scripts optionally read WEATHER_ENSEMBLE_API_KEY and WEATHER_ENSEMBLE_HOST (both reasonable and documented). No unrelated secrets or config paths are requested.
Persistence & Privilege
Skill is not always-on and does not request elevated persistence. It doesn't modify other skills or agent config. Normal autonomous invocation settings remain (not a special privilege).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install weather-ensemble-forecast - After installation, invoke the skill by name or use
/weather-ensemble-forecast - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: compare up to 9 weather models side-by-side for 16 global cities
Metadata
Frequently Asked Questions
What is Weather Ensemble Forecast?
Multi-model ensemble weather forecasts comparing GFS, ECMWF, JMA, GEM, ICON, ARPEGE, GraphCast and more. Get high temperature predictions from up to 9 indepe... It is an AI Agent Skill for Claude Code / OpenClaw, with 294 downloads so far.
How do I install Weather Ensemble Forecast?
Run "/install weather-ensemble-forecast" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Weather Ensemble Forecast free?
Yes, Weather Ensemble Forecast is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Weather Ensemble Forecast support?
Weather Ensemble Forecast is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Weather Ensemble Forecast?
It is built and maintained by Lucasnocodo (@lucasnocodo); the current version is v1.0.0.
More Skills