agentleFS
c-monganc-mongan/ireland-mcp/skills/commute-weather/SKILL.md

commute-weather

Skill2 starsChanged 20 days agoMITView on GitHub

Gives a live Irish commute check combining Irish Rail departures, Luas tram forecasts, NTA bus/rail realtime delays, and the Met Éireann forecast and weather warnings through the Ireland MCP server. Use when someone asks when the next train or Luas is, whether their commute is disrupted, or whether to expect rain or wind on the way to work or school in Ireland.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If an argument shape is unclear, call ireland_describe with { "source", "operation" } first.

    line 24
  2. Very specific:

    Train (DART, commuter, intercity): Call irish-rail/rail_find_station with { "query": "Bray" } to get the exact name, then …

    line 33
  3. Very specific:

    Luas: If unsure of the stop, call luas/luas_list_stops with { "line": "Green" }, then luas/luas_get_forecast with { "stop": "Ranelagh" }.

    line 35
  4. Very specific:

    Bus and other NTA services: Call nta/nta_get_trip_updates with a route_id or stop_id if known, or nta/nta_get_realtime_summary for a …

    line 37
  5. Very specific:

    Weather: Call met-eireann/met_get_forecast with the start point lat/lon and hours (e.g.

    line 39
  6. Distinctive:

    Follow ../_shared/citations.md.

    line 60
  7. Distinctive:

    Never invent timetable data from memory.

    line 63

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Commute and weather check

Answer "how is my journey looking right now?" with live, timestamped data.

Related projects: EZ Commute IE (Rituraj Sambherao), Live Dublin Trains (Jake McDermott). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

Steps name each operation as source/operation (e.g. ppr/ppr_price_stats), using the typed tool name as the operation. On the default surface, run it with ireland_call, for example:

{ "source": "irish-rail", "operation": "rail_get_departures", "args": { "station": "Bray", "minutes": 60 } }

If an argument shape is unclear, call ireland_describe with { "source", "operation" } first; it returns the schema and an example. search, fetch and nearby are top-level tools. If the server was added with ?toolsets=<ids> or ?toolsets=all, the typed tool (e.g. rail_get_departures) can be called directly with the same args.

Steps

  1. Ask for or infer the start stop/station, mode and rough time. Default to "now".
  2. Train (DART, commuter, intercity). Call irish-rail/rail_find_station with { "query": "Bray" } to get the exact name, then irish-rail/rail_get_departures with { "station": "Bray", "minutes": 60 }.
  3. Luas. If unsure of the stop, call luas/luas_list_stops with { "line": "Green" }, then luas/luas_get_forecast with { "stop": "Ranelagh" }.
  4. Bus and other NTA services. Call nta/nta_get_trip_updates with a route_id or stop_id if known, or nta/nta_get_realtime_summary for a network-wide view of delays and cancellations.
  5. Weather. Call met-eireann/met_get_forecast with the start point lat/lon and hours (e.g. 3), and met-eireann/met_get_warnings with {}. Mention only warnings covering the route's counties.
  6. Summarise in one line first, then the detail.

Output format

**Bray → city, as of 08:12:** next DART 08:19 (on time), then 08:34 (+4 min). Light rain, 9°C, no warnings.

| Due | Service | Destination | Status |
|---|---|---|---|
| 08:19 | DART | Howth | on time |

Weather (Met Éireann, issued 07:00): 9°C, rain 0.4 mm/h, wind 25 km/h SW.
Sources
- Irish Rail realtime API, retrieved 08:12
- Met Éireann (CC BY 4.0), forecast issued 07:00

Rules

  • Follow ../_shared/citations.md. Every time is "as of" the retrieval time.
  • Live feeds can lag or be empty. If a feed returns nothing, say "no live data" rather than "no services".
  • Copy warning levels exactly (Yellow/Orange/Red). No safety advice beyond pointing to met.ie and the operator.
  • Never invent timetable data from memory.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.