How do I install the Airquality skill?

Run npx skillmds@latest add seokhoonj/airquality in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Airquality safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Airquality?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Airquality free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Airquality?

seokhoonj (@seokhoonj) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Airquality by seokhoonj — Agent Skill

Name: Airquality
Author: seokhoonj

Airquality

Fetch 한국환경공단 에어코리아 대기오염정보 (AirKorea real-time air quality) from data.go.kr (service B552584) -- 미세먼지(PM10)·초미세먼지(PM2.5)·오존·통합대기환경지수 등, by 시도 (`by_sido`) or by 측정소 (`by_station`). Holds no logic of its own -- it calls the pydatagokr package's CLI (`datagokr airquality`) and shows the result to the user. Trigger phrases: 미세먼지, 초미세먼지, 대기오염, 대기질, 오존, 에어코리아, 통합대기환경지수, air quality, PM10, PM2.5, fine dust.

seokhoonj 1055a95 2.9 KB Updated Sep 17, 2026

File contents

datagokr — 에어코리아 대기오염정보

Fetch real-time air quality. Clean columns: station, measured_at, khai/khai_grade (통합대기환경지수), and per pollutant a value + _grade + _flag: pm10/pm25 (미세먼지· 초미세먼지, ㎍/㎥, integers), so2/co/o3/no2 (ppm, decimals). Grades: 1 좋음 · 2 보통 · 3 나쁨 · 4 매우나쁨.

operation	조회
`by_sido`	시도별 실시간 (a province's stations, latest)
`by_station`	측정소별 실시간 (one station over a term)

Prerequisite

pipx install pydatagokr      # or: pip install pydatagokr

Never print the key value (the DATAGOKR_API_KEY env var or credentials.json) to output, logs, or a summary -- if you need to check which form it is (encoding vs decoding), ask the user.

A data.go.kr decoding key must be configured (env DATAGOKR_API_KEY or ~/.config/pydatagokr/credentials.json), and the 대기오염정보 dataset (service B552584) applied for (활용신청). It is 자동승인 for a development account.

Running

datagokr airquality by_sido <시도명>                         [--json]
datagokr airquality by_station <측정소명> [--data-term TERM] [--json]

<시도명>: 서울 / 부산 / 인천 / 경기 / ... (a 광역시도).
<측정소명>: a station, e.g. 종로구. --data-term is DAILY (default) / MONTH / 3MONTH.

Procedure

Pick the query. "서울 미세먼지" -> by_sido 서울; a named station over time -> by_station <name> --data-term MONTH.
Run.
```
datagokr airquality by_sido 서울
```
Add --json for machine-readable data.
Relay the result. Report pm10/pm25 with their grade (좋음/보통/나쁨/매우나쁨). A _flag value means that pollutant's measurement was unavailable.
Error handling. A one-line datagokr: <message> on stderr:
- a [30]/[20] auth error -> the key is wrong, is the encoding form, or service B552584 is not applied for yet.
- a SERVICETIMEOUT (by_station especially) is a transient AirKorea server timeout -- retry.

What this skill does not do

It does not re-implement fetching or parsing (the package does); it always calls the CLI.
It does not forecast; it returns measurements. (Air-quality forecasts are a separate operation not wrapped here.)

---name: airqualitydescription: Fetch 한국환경공단 에어코리아 대기오염정보 (AirKorea real-time air quality) from data.go.kr (service B552584) -- 미세먼지(PM10)·초미세먼지(PM2.5)·오존·통합대기환경지수 등, by 시도 (`by_sido`) or by 측정소 (`by_station`). Holds no logic of its own -- it calls the pydatagokr package's CLI (`datagokr airquality`) and shows the result to the user. Trigger phrases: 미세먼지, 초미세먼지, 대기오염, 대기질, 오존, 에어코리아, 통합대기환경지수, air quality, PM10, PM2.5, fine dust.---# datagokr — 에어코리아 대기오염정보Fetch real-time air quality. Clean columns: `station`, `measured_at`, `khai`/`khai_grade`(통합대기환경지수), and per pollutant a value + `_grade` + `_flag`: `pm10`/`pm25` (미세먼지·초미세먼지, ㎍/㎥, integers), `so2`/`co`/`o3`/`no2` (ppm, decimals). Grades: 1 좋음 · 2 보통 ·3 나쁨 · 4 매우나쁨.| operation | 조회 ||---|---|| `by_sido` | 시도별 실시간 (a province's stations, latest) || `by_station` | 측정소별 실시간 (one station over a term) |## Prerequisite```pipx install pydatagokr # or: pip install pydatagokr```**Never print the key value** (the `DATAGOKR_API_KEY` env var or `credentials.json`) to output, logs, or a summary -- if you need to check which form it is (encoding vs decoding), ask the user.A data.go.kr **decoding** key must be configured (env `DATAGOKR_API_KEY` or`~/.config/pydatagokr/credentials.json`), and the 대기오염정보 dataset (service B552584)applied for (활용신청). It is 자동승인 for a development account.## Running```datagokr airquality by_sido <시도명> [--json]datagokr airquality by_station <측정소명> [--data-term TERM] [--json]```- `<시도명>`: 서울 / 부산 / 인천 / 경기 / ... (a 광역시도).- `<측정소명>`: a station, e.g. 종로구. `--data-term` is `DAILY` (default) / `MONTH` / `3MONTH`.## Procedure1. **Pick the query.** "서울 미세먼지" -> `by_sido 서울`; a named station over time -> `by_station <name> --data-term MONTH`.2. **Run.** ```bash datagokr airquality by_sido 서울 ``` Add `--json` for machine-readable data.3. **Relay the result.** Report `pm10`/`pm25` with their grade (좋음/보통/나쁨/매우나쁨). A `_flag` value means that pollutant's measurement was unavailable.4. **Error handling.** A one-line `datagokr: <message>` on stderr: - a `[30]`/`[20]` auth error -> the key is wrong, is the *encoding* form, or service B552584 is not applied for yet. - a `SERVICETIMEOUT` (`by_station` especially) is a transient AirKorea server timeout -- retry.## What this skill does not do- It does not re-implement fetching or parsing (the package does); it always calls the CLI.- It does not forecast; it returns measurements. (Air-quality forecasts are a separate operation not wrapped here.)

Frequently asked questions