agentleFS
c-monganc-mongan/ireland-mcp/skills/transport-reliability-check/SKILL.md

transport-reliability-check

Skill2 starsChanged 19 days agoMITView on GitHub

Takes a live reliability snapshot of Irish public transport - Irish Rail, DART and commuter lateness at a station, Luas arrivals and disruption messages, and, where the server has NTA real-time configured, bus and rail trip cancellations and delays by route - via the Ireland MCP server. Use when someone asks whether trains are running late, if the Luas is disrupted, which bus routes are cancelling trips right now, or wants a quick "is it running" check before travelling.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    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 28
  2. Very specific:

    Rail: Call irish-rail/rail_find_station if the station name is ambiguous, then irish-rail/rail_get_departures with { "station", "minutes": …

    line 35
  3. Very specific:

    Luas: Call luas/luas_get_forecast with { "stop": "<name or code>" }.

    line 38
  4. Very specific:

    Bus and network-wide (if configured): Call nta/nta_get_realtime_summary with { "limit": 20 } for routes with the most cancellations and …

    line 41
  5. Distinctive:

    Follow ../_shared/citations.md.

    line 65
  6. Distinctive:

    No historical claims (e.g.

    line 68

≈ “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

Transport reliability check

A point-in-time snapshot of how services are running now. It cannot show history or trends; it only reports what the live feeds return at the moment of the call. Use commute-weather for a journey plus weather.

Related projects: Ghost Buster (Oliver Moran), Bus Cancellations Dublin (Unknown), No-Show Bus Tracker (Dublin Inquirer), Live Dublin Trains (Jake McDermott), EZ Commute IE (Rituraj Sambherao). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

Steps name each operation as source/operation (e.g. irish-rail/rail_get_departures), 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": "Connolly", "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 can be called directly with the same args.

Steps

  1. Rail. Call irish-rail/rail_find_station if the station name is ambiguous, then irish-rail/rail_get_departures with { "station", "minutes": 60 }. Count trains, those with late_min of 5 or more, and the maximum lateness. Note "No Information" statuses separately.
  2. Luas. Call luas/luas_get_forecast with { "stop": "<name or code>" }. Report the message verbatim (it carries disruption notices) and the next arrivals each way. Use luas/luas_list_stops to find a stop code.
  3. Bus and network-wide (if configured). Call nta/nta_get_realtime_summary with { "limit": 20 } for routes with the most cancellations and delays. For one route or stop, nta/nta_get_trip_updates with route_id or stop_id (a GTFS id, e.g. "8220DB000007"). If the response is NOT_CONFIGURED, say that live bus data is not available on this server and continue with rail and Luas.
  4. Stops near a point (optional). tfi-static/tfi_static_search_stops with { "lat", "lon", "radius": 500 } for nearby stop names; NaPTAN AtcoCodes are not guaranteed to equal GTFS stop ids.
  5. Timestamp everything. Give the time of each call; a snapshot ages within minutes.

Output format

Illustrative layout; the values are examples, not data.

## Running now — 13:38, 26 Oct 2026
**Dublin Connolly (next 60 min):** 8 trains, 1 running ≥5 min late (max 6 min), 1 with no information
**Luas Abbey Street:** "Sunday operating hours & frequency today" — next Connolly 3 min, Saggart 1 min
**Bus (NTA):** not available on this server (NTA real-time not configured)
Sources
- Irish Rail realtime API; TII Luas Forecasting API (CC BY 4.0); NTA GTFS-Realtime (CC BY 4.0)

Rules

  • Follow ../_shared/citations.md; live feeds can be delayed or empty.
  • Report counts, not judgements ("unreliable", "ghost bus"). A trip missing from a feed is not proof it did not run.
  • No historical claims (e.g. "worst this month"); this skill sees only the current snapshot.

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.