Oebb Scotty logo

Oebb Scotty

CommunityPopular
mitsuhiko
oebb-scotty

Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

Overview

Publishermitsuhiko
Repositoryagent-stuff
Skill nameoebb-scotty
Stars
3.1K
Forks
224
Bundled files
5
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mitsuhiko on GitHub. Read the source before you install it.

Installation

Install the Oebb Scotty AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mitsuhiko/agent-stuff.git /tmp/agent-stuff
mkdir -p .claude/skills
cp -r /tmp/agent-stuff/skills/oebb-scotty .claude/skills/oebb-scotty
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oebb Scotty in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Oebb Scotty on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Oebb Scotty is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ÖBB Scotty API

Query Austria's public transport for trip planning, station departures, and service alerts via the HAFAS mgate API.

Quick Reference

MethodPurpose
LocMatchSearch for stations/stops by name
TripSearchPlan a journey between two locations
StationBoardGet departures/arrivals at a station
HimSearchGet service alerts and disruptions

Base URL: https://fahrplan.oebb.at/bin/mgate.exe


Authentication

All requests require these headers in the JSON body:

json
{
  "id": "1",
  "ver": "1.67",
  "lang": "deu",
  "auth": {"type": "AID", "aid": "OWDL4fE4ixNiPBBm"},
  "client": {"id": "OEBB", "type": "WEB", "name": "webapp", "l": "vs_webapp"},
  "formatted": false,
  "svcReqL": [...]
}

1. Location Search (LocMatch)

Search for stations, stops, addresses, or POIs by name.

Request

bash
curl -s -X POST "https://fahrplan.oebb.at/bin/mgate.exe" \
  -H "Content-Type: application/json" \
  -d '{
    "id":"1","ver":"1.67","lang":"deu",
    "auth":{"type":"AID","aid":"OWDL4fE4ixNiPBBm"},
    "client":{"id":"OEBB","type":"WEB","name":"webapp","l":"vs_webapp"},
    "formatted":false,
    "svcReqL":[{
      "req":{"input":{"field":"S","loc":{"name":"Wien Hbf","type":"ALL"},"maxLoc":10}},
      "meth":"LocMatch"
    }]
  }'

Response Structure

json
{
  "svcResL": [{
    "res": {
      "match": {
        "locL": [{
          "lid": "A=1@O=Wien Hbf (U)@X=16377950@Y=48184986@U=181@L=1290401@",
          "type": "S",
          "name": "Wien Hbf (U)",
          "extId": "1290401",
          "crd": { "x": 16377950, "y": 48184986 },
          "pCls": 6015
        }]
      }
    }
  }]
}

Location Types

TypeDescription
SStation/Stop
AAddress
PPOI (Point of Interest)

Key Fields

FieldDescription
lidLocation ID string (use in TripSearch)
extIdExternal station ID
nameStation name
crd.x/yCoordinates (x=lon, y=lat, scaled by 10^6)
pClsProduct class bitmask

2. Trip Search (TripSearch)

Plan a journey between two locations.

Request

bash
curl -s -X POST "https://fahrplan.oebb.at/bin/mgate.exe" \
  -H "Content-Type: application/json" \
  -d '{
    "id":"1","ver":"1.67","lang":"deu",
    "auth":{"type":"AID","aid":"OWDL4fE4ixNiPBBm"},
    "client":{"id":"OEBB","type":"WEB","name":"webapp","l":"vs_webapp"},
    "formatted":false,
    "svcReqL":[{
      "req":{
        "depLocL":[{"lid":"A=1@O=Wien Hbf@L=8103000@","type":"S"}],
        "arrLocL":[{"lid":"A=1@O=Salzburg Hbf@L=8100002@","type":"S"}],
        "jnyFltrL":[{"type":"PROD","mode":"INC","value":"1023"}],
        "getPolyline":false,
        "getPasslist":true,
        "outDate":"20260109",
        "outTime":"080000",
        "outFrwd":true,
        "numF":5
      },
      "meth":"TripSearch"
    }]
  }'

Parameters

ParamDescription
depLocLDeparture location(s) - use lid from LocMatch
arrLocLArrival location(s)
outDateDeparture date (YYYYMMDD)
outTimeDeparture time (HHMMSS)
outFrwdtrue = search forward, false = search backward
numFNumber of connections to return
jnyFltrLProduct filter (see below)
getPasslistInclude intermediate stops

Product Filter Values

BitValueProduct
01ICE/RJX (High-speed)
12IC/EC (InterCity)
24NJ (Night trains)
38D/EN (Express)
416REX/R (Regional Express)
532S-Bahn
664Bus
7128Ferry
8256U-Bahn
9512Tram

Use 1023 for all products, or sum specific bits.

Response Structure

json
{
  "svcResL": [{
    "res": {
      "outConL": [{
        "date": "20260109",
        "dur": "025200",
        "chg": 0,
        "dep": {
          "dTimeS": "075700",
          "dPltfS": {"txt": "8A-B"}
        },
        "arr": {
          "aTimeS": "104900",
          "aPltfS": {"txt": "7"}
        },
        "secL": [{
          "type": "JNY",
          "jny": {
            "prodX": 0,
            "dirTxt": "Salzburg Hbf",
            "stopL": [...]
          }
        }]
      }],
      "common": {
        "locL": [...],
        "prodL": [...]
      }
    }
  }]
}

Key Connection Fields

FieldDescription
durDuration (HHMMSS)
chgNumber of changes
dTimeSScheduled departure
dTimeRReal-time departure (if available)
aTimeSScheduled arrival
aTimeRReal-time arrival (if available)
dPltfS.txtDeparture platform
aPltfS.txtArrival platform
secLJourney sections (legs)
secL[].jny.prodXIndex into common.prodL[] for train name

Understanding prodX (Product Index)

Important: The prodX field in journey sections is an index into the common.prodL[] array, NOT the train name itself. To get the actual train name (e.g., "S7", "RJX 662"), you must look up common.prodL[prodX].name.

Extracting Trip Summaries with jq

The raw TripSearch response is very verbose. Use this jq filter to extract a concise summary with resolved train names:

bash
curl -s -X POST "https://fahrplan.oebb.at/bin/mgate.exe" \
  -H "Content-Type: application/json" \
  -d '{ ... }' | jq '
    .svcResL[0].res as $r |
    $r.common.prodL as $prods |
    [$r.outConL[] | {
      dep: .dep.dTimeS,
      arr: .arr.aTimeS,
      depPlatform: .dep.dPltfS.txt,
      arrPlatform: .arr.aPltfS.txt,
      dur: .dur,
      chg: .chg,
      legs: [.secL[] | select(.type == "JNY") | {
        train: $prods[.jny.prodX].name,
        dir: .jny.dirTxt,
        dep: .dep.dTimeS,
        arr: .arr.aTimeS,
        depPlatform: .dep.dPltfS.txt,
        arrPlatform: .arr.aPltfS.txt
      }]
    }]'

Example output:

json
[
  {
    "dep": "213900",
    "arr": "221100",
    "depPlatform": "1",
    "arrPlatform": "3A-B",
    "dur": "003200",
    "chg": 0,
    "legs": [{"train": "S 7", "dir": "Flughafen Wien Bahnhof", "dep": "213900", "arr": "221100", ...}]
  }
]

3. Station Board (StationBoard)

Get departures or arrivals at a station.

Request

bash
curl -s -X POST "https://fahrplan.oebb.at/bin/mgate.exe" \
  -H "Content-Type: application/json" \
  -d '{
    "id":"1","ver":"1.67","lang":"deu",
    "auth":{"type":"AID","aid":"OWDL4fE4ixNiPBBm"},
    "client":{"id":"OEBB","type":"WEB","name":"webapp","l":"vs_webapp"},
    "formatted":false,
    "svcReqL":[{
      "req":{
        "stbLoc":{"lid":"A=1@O=Wien Hbf@L=8103000@","type":"S"},
        "date":"20260109",
        "time":"080000",
        "type":"DEP",
        "maxJny":20
      },
      "meth":"StationBoard"
    }]
  }'

Parameters

ParamDescription
stbLocStation location
dateDate (YYYYMMDD)
timeTime (HHMMSS)
typeDEP (departures) or ARR (arrivals)
maxJnyMaximum number of journeys

Response Structure

json
{
  "svcResL": [{
    "res": {
      "jnyL": [{
        "prodX": 0,
        "dirTxt": "Salzburg Hbf",
        "stbStop": {
          "dTimeS": "080000",
          "dPltfS": {"txt": "8A-B"}
        }
      }],
      "common": {
        "prodL": [{
          "name": "RJX 662",
          "cls": 1,
          "prodCtx": {"catOutL": "Railjet Xpress"}
        }]
      }
    }
  }]
}

4. Service Alerts (HimSearch)

Get current disruptions and service information.

Request

bash
curl -s -X POST "https://fahrplan.oebb.at/bin/mgate.exe" \
  -H "Content-Type: application/json" \
  -d '{
    "id":"1","ver":"1.67","lang":"deu",
    "auth":{"type":"AID","aid":"OWDL4fE4ixNiPBBm"},
    "client":{"id":"OEBB","type":"WEB","name":"webapp","l":"vs_webapp"},
    "formatted":false,
    "svcReqL":[{
      "req":{
        "himFltrL":[{"type":"PROD","mode":"INC","value":"255"}],
        "maxNum":20
      },
      "meth":"HimSearch"
    }]
  }'

Response Structure

json
{
  "svcResL": [{
    "res": {
      "msgL": [{
        "hid": "HIM_FREETEXT_843858",
        "head": "Verringertes Sitzplatzangebot",
        "text": "Wegen einer technischen Störung...",
        "prio": 0,
        "sDate": "20260108",
        "eDate": "20260108"
      }]
    }
  }]
}

Common Station IDs

StationextId
Wien Hbf8103000
Wien Meidling8100514
Wien Westbahnhof8101003
Salzburg Hbf8100002
Linz Hbf8100013
Graz Hbf8100173
Innsbruck Hbf8100108
Klagenfurt Hbf8100085
St. Pölten Hbf8100008
Wr. Neustadt Hbf8100516

Time Format

  • Dates: YYYYMMDD (e.g., 20260109)
  • Times: HHMMSS (e.g., 080000 = 08:00:00)
  • Duration: HHMMSS (e.g., 025200 = 2h 52m)

Error Handling

Check err field in response:

json
{
  "err": "OK",           // Success
  "err": "PARSE",        // Invalid request format
  "err": "NO_MATCH",     // No results found
  "errTxt": "..."        // Error details
}

Product Classes (cls values)

clsProduct
1ICE/RJX
2IC/EC
4Night trains
8NJ/EN
16REX/Regional
32S-Bahn
64Bus
128Ferry
256U-Bahn
512Tram
1024On-demand
2048Other

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Oebb Scotty AI skill do?

Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

Why use Oebb Scotty on TypingMind?

Because you install it once and use it with any model. Oebb Scotty is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Oebb Scotty in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mitsuhiko/agent-stuff/tree/main/skills/oebb-scotty. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Oebb Scotty?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Oebb Scotty?

As many as you like. As long as a model supports skills, you can use Oebb Scotty with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Oebb Scotty AI skill free?

Yes. It is published on GitHub by mitsuhiko under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇