FrancyJGLisboa/agent-skills-platform / references/examples/live-weather-briefing-skill
live-weather-briefing-skill
UnverifiedCreate a current, source-linked weather briefing for a named city using the Open-Meteo geocoding and forecast APIs. Activate for requests such as "what is the weather in Sao Paulo?", "prepare a current weather briefing for Tokyo", or "get today's live conditions for New York". Do not use for travel booking, weather alerts, historical climatology, or safety-critical decisions.
evals/live-weather-briefing.eval.md
View on GitHub# Eval Spec: live-weather-briefing-skill
Each rollout makes a real, read-only API request. Conditions naturally change, so
the checks validate briefing structure rather than pinning a weather value.
```json
{
"skill": "live-weather-briefing-skill",
"run": "python3 scripts/run_pipeline.py --input {input} --output {output}",
"criteria": [
{"id": "title", "text": "Names a current weather briefing", "type": "command", "cmd": "grep -q '^# Current weather:' {output}"},
{"id": "conditions", "text": "Contains the required current-condition fields", "type": "command", "cmd": "grep -q '^- Temperature:' {output} && grep -q '^- Feels like:' {output} && grep -q '^- Wind:' {output}"},
{"id": "provenance", "text": "Includes both live source URLs", "type": "command", "cmd": "grep -q 'Geocoding: https://geocoding-api.open-meteo.com' {output} && grep -q 'Forecast: https://api.open-meteo.com' {output}"}
],
"golden": [
{"id": "sao-paulo", "input": "golden/sao-paulo/input.txt", "expected": null, "split": "val", "expected_status": "pending-first-green", "compare": "none"},
{"id": "new-york", "input": "golden/new-york/input.txt", "expected": null, "split": "val", "expected_status": "pending-first-green", "compare": "none"},
{"id": "tokyo", "input": "golden/tokyo/input.txt", "expected": null, "split": "test", "expected_status": "pending-first-green", "compare": "none"}
]
}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |