FrancyJGLisboa/agent-skills-platform / .agents/skills/live-weather-briefing-skill
live-weather-briefing-skill
VerifiedCreate 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.
| File | Kind | Size |
|---|---|---|
| .claude-plugin/marketplace.json | config | 378 B |
| .claude-plugin/plugin.json | config | 225 B |
| AGENTS.md | markdown | 664 B |
| EVOLUTION.md | markdown | 745 B |
| SKILL.md | skill md | 2.3 KB |
| discovery.json | config | 2.1 KB |
| evals/golden/new-york/input.txt | markdown | 13 B |
| evals/golden/sao-paulo/input.txt | markdown | 14 B |
| evals/golden/tokyo/input.txt | markdown | 10 B |
| evals/live-weather-briefing.eval.md | markdown | 1.4 KB |
| install.ps1 | script | 24.7 KB |
| interview.json | config | 5.6 KB |
| scripts/dependency_health.py | script | 3.9 KB |
| scripts/evolve.py | script | 10.2 KB |
| scripts/review_staleness.py | script | 6.2 KB |
| scripts/run_evals.py | script | 49.4 KB |
| scripts/run_pipeline.py | script | 4.7 KB |
| scripts/schema_drift.py | script | 7.3 KB |
| scripts/skill_document.py | script | 9.8 KB |
| scripts/staleness_check.py | script | 7.5 KB |
| scripts/success_ledger.py | script | 16.3 KB |
| skill.graph.json | config | 5.3 KB |
scripts/dependency_health.py
View on GitHub#!/usr/bin/env python3
"""
Dependency health check for a skill.
Issues an HTTP HEAD to each declared dependency URL and reports whether the
endpoint is reachable, returning a normal status, or has moved / errored.
Non-HTTP URLs and URLs without a scheme are reported as skipped.
"""
from __future__ import annotations
from urllib.error import HTTPError, URLError
from urllib.request import Request, urlopen
HTTP_TIMEOUT_SECONDS = 10
_USER_AGENT = "agent-skill-staleness-check/1.0"
def check_dependency_health(dependencies: list[dict]) -> list[dict]:
"""
Probe each dependency's URL. Returns a list of issue dicts (level, message,
detail). Status thresholds:
2xx-3xx -> info "healthy"
4xx -> warning "client error / may have moved"
5xx -> error "server error"
URLError, other -> error "unreachable / check failed"
"""
issues: list[dict] = []
for dep in dependencies:
url = dep.get("url", "").strip()
name = dep.get("name", url)
if not url:
issues.append({
"level": "warning",
"message": f"Dependency '{name}' has no URL",
"detail": "Cannot check health without a URL.",
})
continue
if not url.startswith(("http://", "https://")):
issues.append({
"level": "warning",
"message": f"Dependency '{name}' has non-HTTP URL",
"detail": f"Skipping health check for: {url}",
})
continue
try:
req = Request(url, method="HEAD")
req.add_header("User-Agent", _USER_AGENT)
with urlopen(req, timeout=HTTP_TIMEOUT_SECONDS) as resp:
status = resp.status
if 200 <= status < 400:
issues.append({
"level": "info",
"message": f"Dependency '{name}' is healthy",
"detail": f"HTTP {status} from {url}",
})
elif 400 <= status < 500:
issues.append({
"level": "warning",
"message": f"Dependency '{name}' returned client error",
"detail": f"HTTP {status} from {url}. "
"The endpoint may have moved or require authentication.",
})
else:
issues.append({
"level": "error",
"message": f"Dependency '{name}' returned server error",
"detail": f"HTTP {status} from {url}",
})
except HTTPError as exc:
# urlopen RAISES on 4xx/5xx; HTTPError subclasses URLError, so this
# must be caught first or every error status reads as "unreachable".
if 400 <= exc.code < 500:
issues.append({
"level": "warning",
"message": f"Dependency '{name}' returned client error",
"detail": f"HTTP {exc.code} from {url}. "
"The endpoint may have moved or require authentication.",
})
else:
issues.append({
"level": "error",
"message": f"Dependency '{name}' returned server error",
"detail": f"HTTP {exc.code} from {url}",
})
except URLError as exc:
issues.append({
"level": "error",
"message": f"Dependency '{name}' is unreachable",
"detail": f"Failed to connect to {url}: {exc.reason}",
})
except Exception as exc:
issues.append({
"level": "error",
"message": f"Dependency '{name}' check failed",
"detail": f"Error checking {url}: {exc}",
})
return issues
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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |