seoul-subway-crowd
Skill3 starsChanged 10 days agoMITView on GitHub
Query and summarize Seoul subway congestion statistics via SK Open API (TMAP 대중교통). Use when the user asks for station/line-based train congestion or car-by-car congestion, time-slot checks (dow/hh), comparisons, or commute alerts.
- Reads credentials
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acp-discord-orchestratorSkill
- brave-api-setupSkill
- daum-trendsSkill
- ipo-alertSkill
- ku-portalSkill
- music-preference-recoSkill
- nano-banana-proSkill
- olympic-alertSkill
- tistory-publishSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Ensure SK_OPENAPI_KEY exists in environment.
- Very specific: line 16
Read endpoint and parameter mapping from references/api-map.md.
- Very specific: line 17
Run scripts/fetch_crowd.py with station/line/time arguments.
- Distinctive: line 22
If API fails, return clear fallback with reason and next action.
- Distinctive: line 31
Keep it short and practical.
- Distinctive: line 32
Prefer bullet list over tables on Discord.
- Distinctive: line 36
Do not hardcode API key.
- Very specific: line 38
If API schema changes, update references/api-map.md first.
≈ “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.
Files
Seoul Subway Crowd (SK Open API)
Inputs to collect
- Station name (required)
- Line name/number (optional but recommended)
- Direction (optional): up/down or inbound/outbound
- Time mode (optional): now/forecast
Workflow
- Ensure
SK_OPENAPI_KEYexists in environment. - Read endpoint and parameter mapping from
references/api-map.md. - Run
scripts/fetch_crowd.pywith station/line/time arguments. - Return a short Korean summary:
- 혼잡도 등급
- 핵심 수치(있으면)
- 한 줄 코멘트(이동 추천/회피 시간)
- If API fails, return clear fallback with reason and next action.
CLI usage
python3 scripts/fetch_crowd.py --station "강남역" --line "2호선" --mode train
python3 scripts/fetch_crowd.py --station "홍대입구역" --line "2호선" --mode car --dow MON --hh 08Output style
- Keep it short and practical.
- Prefer bullet list over tables on Discord.
- Include raw response path when debugging (
--save-json).
Notes
- Do not hardcode API key.
- Normalize common line variants ("2", "2호선", "Line 2").
- If API schema changes, update
references/api-map.mdfirst.
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
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.

