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

weather-forecast

Skill97 starsChanged 33 days agoApache-2.0View on GitHub

Normalize supplied provider weather evidence into a provenance-bound forecast packet with uncertainty and stop conditions. Use when a downstream planning workflow needs provider-neutral weather context; do not use it to fetch forecasts, make life-safety decisions, or perform downstream actions.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read only forecast_evidence.

    line 15

≈ “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

Weather Forecast

Interpret supplied weather evidence, then let the deterministic finalizer bind the result to that evidence.

This skill is read-only. It does not fetch forecasts, send alerts, change schedules, or mutate provider state. Use nws-weather-forecast, open-meteo-weather-forecast, or another provider skill to obtain evidence first.

Procedure

  1. Identify the requested location, horizon, purpose, and freshness requirement.
  2. Read only forecast_evidence. Do not add provider references, timestamps, or forecast periods that are absent from it.
  3. Assess whether the evidence is fresh and complete enough for the stated purpose. Return needs_more_evidence when it is stale, ambiguous, unsupported, or too thin.
  4. Summarize relevant periods, uncertainty, hazards, and planning implications without claiming a downstream action occurred.
  5. Return refused for emergency, evacuation, aviation, maritime, medical, or other life-safety use.

The finalizer enforces the requested location and horizon, context-only authority, provider identity, provenance references, generation timestamp, and period-name fidelity. A draft that invents any of those fails instead of sealing a forecast packet.

Output

decision: ready | needs_input | needs_more_evidence | refused
location: string
horizon: string
forecast_packet:
  summary: string
  periods: array
  hazards: array
  confidence: string
  generated_at: string
provider_evidence:
  provider: string
  source_refs: array
  receipt_refs: array
safety_notes: array
stop_conditions: array
receipt_notes:
  authority: context-only
  mutation: false

For ready, the supplied evidence must include provider, generated_at, periods, and at least one source_ref or receipt_ref. Missing forecast_evidence stops before agent interpretation. A missing optional horizon remains an empty string; the agent must not invent one.

Agent task contracts

weather-forecast-interpret

Interpret only the supplied forecast evidence and return forecast_draft using the documented output fields. Preserve the requested location and horizon, provider, generated_at, source_refs, receipt_refs, and relevant period names. Summaries, hazards, uncertainty, and stop conditions require analyst judgment, but do not invent evidence. Return needs_more_evidence when freshness or coverage is insufficient. Return refused for life-safety use.

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.