seoul-weather-risk

Query forecast-based weather risk windows for Seoul administrative dongs via a hosted proxy API.

7.4k|904|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/NomaDamas/k-skill --skill seoul-weather-risk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: seoul-weather-risk
Source: https://github.com/NomaDamas/k-skill/tree/main/seoul-weather-risk
Command: npx skills add https://github.com/NomaDamas/k-skill --skill seoul-weather-risk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Checking whether a specific Seoul neighborhood faces heat waves, cold snaps, heavy rain, snow, or strong winds during a planned visit requires manually interpreting raw forecast data. This Skill resolves a Seoul administrative dong name to its official place_id and retrieves read-only, forecast-based weather risk time windows from the ASK Seoul data product through the hosted k-skill proxy, with no user API key required.

Core Features & Use Cases

  • Deterministic location resolution: Maps any of Seoul's 427 administrative dongs to a canonical place_id using exact-name matching plus strictly defined notation aliases, with gu-based disambiguation for duplicate names like Sinsa-dong.
  • Read-only risk window queries: Retrieves the weather_place_risk_window product (heat, cold, rain, snow, wind candidates by forecast time) via a single fast-path query with automatic date-range expansion and one retry against the available forecast window.
  • Strict contract validation: Verifies bundle, product, and data response contracts and never substitutes fixtures or estimates for failed live queries.
  • Use Case: Ask "What weather risk time windows should I watch for when visiting Jamsilbon-dong today?" and receive the forecast-based risk periods with publication metadata and row counts.

Quick Start

Ask the assistant to check today's weather risk time windows for a Seoul neighborhood, for example: "Tell me the weather risk hours and their basis for Jamsilbon-dong today."

Frequently Asked Questions about seoul-weather-risk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check weather risk for a Seoul neighborhood?

Provide the Seoul administrative dong name in natural language, and the skill resolves it to a place_id and queries the weather_place_risk_window product through the hosted k-skill proxy. No API key or place_id knowledge is needed; dates like today or tomorrow are converted to explicit KST ranges.

What weather hazards does the Seoul weather risk query cover?

The product surfaces forecast-based candidate windows for heat waves, cold snaps, heavy rain, heavy snow, and strong winds, filtered by thresholds. It is reference information derived from forecast values, not an official Korea Meteorological Administration warning.

Do I need an API key to query Seoul weather risk data?

No user API key is required. The helper calls the hosted k-skill proxy, which holds the operator-managed ASK Seoul service key, and never reads local .env files or user credentials.

Why does my Seoul dong name return unknown_admin_dong?

The resolver only accepts exact official administrative dong names plus limited deterministic aliases, such as omitting the 'je' prefix before numbers or varying numeric separators. Typos, colloquial names, or partial names like 'Seongsu-dong' are rejected rather than fuzzy matched.

What happens when two Seoul dongs share the same name?

Names like Sinsa-dong exist in both Gangnam-gu and Gwanak-gu, so the query returns ambiguous_admin_dong with candidate districts. You must supply the gu name to disambiguate before the query proceeds.

Why did my weather risk query return query_window_unavailable?

The requested date range does not overlap the currently served forecast window. The helper retries once against the intersection of your range and the available window; if none exists, it reports the available_from_at and available_to_at bounds instead of fabricating data.