agentleFS
runxhqrunxhq/runx/skills/open-meteo-weather-forecast/SKILL.md

open-meteo-weather-forecast

Skill97 starsChanged 35 days agoApache-2.0View on GitHub

Resolve a place and fetch global forecast and air-quality evidence through governed, keyless Open-Meteo HTTP calls.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run locate with a city or place name.

    line 17
  2. Very specific:

    Run the default forecast runner with the selected coordinates.

    line 20
  3. Distinctive:

    Treat the result as context only.

    line 23
  4. Distinctive:

    Mutation requested from forecast evidence: stop after the sealed read and require a separate authority-scoped action skill.

    line 60
  5. Very specific:

    Run locate with name: Shanghai.

    line 65
  6. Very specific:

    Run forecast using the sealed latitude and longitude with forecast_days: "3".

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Open-Meteo Weather Forecast

Fetch global place, forecast, and air-quality evidence through runx's governed HTTP front. The skill never performs an ad-hoc fetch. Each stage is a bounded, read-only HTTP runner whose endpoint, inputs, status, authority scope, and output packet are recorded in the sealed receipt. Open-Meteo requires no API key and covers the whole globe, so this is the worldwide counterpart to the US-only nws-weather-forecast provider.

Procedure

  1. Run locate with a city or place name.
  2. Select the intended result and preserve its latitude, longitude, timezone, and country as a typed provider-evidence packet.
  3. Run the default forecast runner with the selected coordinates.
  4. Require a 2xx response and preserve the provider URL, timezone, generation time, current conditions, daily forecast, and receipt references.
  5. Treat the result as context only. Any notification, scheduling change, or operational mutation requires a separate skill and authority gate.

Inputs

  • name (locate, required): city or place to resolve.
  • count (locate, optional): maximum candidate results, default 5.
  • latitude (forecast, required): decimal latitude.
  • longitude (forecast, required): decimal longitude.
  • forecast_days (forecast, optional): days requested, default 3.

Output packets

Two runners are exposed. The default main runner runs locate then forecast. The air_quality runner runs locate then air_quality. Each graph step produces a typed sealed packet:

  • locate produces Open-Meteo geocoding provider evidence.
  • forecast produces Open-Meteo forecast provider evidence.
  • air_quality produces Open-Meteo air-quality provider evidence (PM2.5, PM10, carbon monoxide, nitrogen dioxide, sulphur dioxide, ozone, and the European and US air-quality indices).

Preserve provider metadata and receipt references when passing either packet to another skill. Do not convert provider evidence into high-stakes advice.

Failure, retry, and stop conditions

  • Ambiguous or missing place: return needs_input; do not silently choose a similarly named location.
  • Invalid coordinates or forecast-days value: return needs_input.
  • Non-2xx response, timeout, or rate limit: return needs_more_evidence, preserve the failure in the receipt, and retry only under the caller's retry policy.
  • Stale or incomplete provider response: return needs_more_evidence.
  • Life-safety, medical, aviation, maritime, or emergency use: refuse and direct the caller to official channels.
  • Mutation requested from forecast evidence: stop after the sealed read and require a separate authority-scoped action skill.

Worked example

  1. Run locate with name: Shanghai.
  2. Select the result for Shanghai, China.
  3. Run forecast using the sealed latitude and longitude with forecast_days: "3".
  4. Preserve both sealed receipts with the returned forecast evidence.

Credits

Combined from two community contributions: the forecast skill (#63, @why123-boop) and the air-quality snapshot (#64, @yanziwei).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.