skanetrafiken

0
0
Source

Skåne public transport trip planner (Skånetrafiken). Plans bus/train journeys with real-time delays. Supports stations, addresses, landmarks, and cross-border trips to Copenhagen.

Install

mkdir -p .claude/skills/skanetrafiken && curl -L -o skill.zip "https://mcp.directory/api/skills/download/9253" && unzip -o skill.zip -d .claude/skills/skanetrafiken && rm skill.zip

Installs to .claude/skills/skanetrafiken

About this skill

Skånetrafiken Trip Planner

Plan public transport journeys in Skåne, Sweden with real-time departure information.

Commands

1. Search Location

Search for stations, addresses, or points of interest.

./search-location.sh <query> [limit]
ArgumentDescription
queryLocation name to search for
limitNumber of results to show (default: 3, max: 10)

Output includes:

  • ID - The location identifier (use this in journey search)
  • Name - Official name of the location
  • Type - STOP_AREA (station), ADDRESS, or POI (point of interest)
  • Area - Region/municipality
  • Coordinates - Latitude, longitude

When to increase limit:

  • First result doesn't match user's intent
  • User's query is ambiguous (e.g., "station", "centrum")
  • Need to show user multiple options to choose from

2. Journey Search

Plan a journey between two locations using their IDs.

./journey.sh <from-id> <from-type> <to-id> <to-type> [datetime] [mode]
ArgumentDescription
from-idOrigin location ID (from search) or coordinates (lat#lon)
from-typeSTOP_AREA, ADDRESS, POI, or LOCATION (for coordinates)
to-idDestination location ID or coordinates
to-typeType of destination
datetimeOptional: "18:30", "tomorrow 09:00", "2026-01-15 09:00"
modeOptional: "depart" (default) or "arrive"

Important: The Journey API only accepts STOP_AREA and LOCATION types. For ADDRESS or POI results, use the coordinates as lat#lon with type LOCATION.


Understanding User Time Intent

Before searching, understand what the user wants:

Intent Types

User SaysIntentHow to Query
"now", "next bus", "how do I get to"Travel NowNo datetime parameter
"in 30 minutes", "in 1 hour", "after lunch"Depart LaterCalculate time, use depart mode
"around 15:00", "sometime afternoon"Around TimeQuery with offset (see below)
"arrive by 18:00", "need to be there at 9"Arrive ByUse arrive mode
"tomorrow morning", "on Friday at 10"Future TimeUse specific datetime

Handling "Around Time" Queries

When user wants options "around" a time, query 15-30 minutes earlier to show options before and after:

# User: "I want to travel around 15:00"
# Query at 14:30 to get options spanning 14:30-16:00+
./journey.sh ... "14:30" depart

Relative Time Calculations

Convert relative times to absolute:

User SaysCurrent: 14:00Query Time
"in 30m""14:30"
"in 1h""15:00"
"in 2 hours""16:00"

LLM Response Formatting

When presenting journey results to users, use these emojis and formatting guidelines.

Emoji Reference

EmojiUse For
🚂Train (Pågatåg, Öresundståg)
🚌Bus
🚇Metro (Copenhagen)
🚋Tram
⛴️Ferry
🚶Walking segment
⏱️Time/duration
🕐Departure time
🏁Arrival time
📍Stop/station
🏠Origin (home/start)
🎯Destination
⚠️Delay or disruption
On time
🔄Transfer/change
🛤️Platform/track

Response Structure

Always include these key elements from the tool output:

  1. When to leave - The actual time user needs to start (including walking)
  2. Walking segments - Distance and time for any walking
  3. Transport departure - When the bus/train actually leaves
  4. Arrival time - When user reaches destination
  5. Any delays - Show deviation from schedule

Example Response Format

For a simple direct journey:

🏠 **Leave home at 09:00**

🚶 Walk 450m to Möllevångstorget (5 min)

📍 **Möllevångstorget** → 🎯 **Malmö C**
🚌 Bus 5 departs 09:07 from Möllevångstorget
🏁 Arrives 09:18 at Malmö C

⏱️ Total: 18 min

For a journey with transfer:

🏠 **Leave at 08:45**

🚶 Walk 300m to Västra Hamnen (4 min)

📍 **Västra Hamnen** → 🔄 **Malmö C** → 🎯 **Lund C**

**Leg 1:**
🚌 Bus 2 departs 08:51 [🛤️ Läge A]
🏁 Arrives Malmö C 09:05

🔄 Transfer at Malmö C (6 min)

**Leg 2:**
🚂 Pågatåg departs 09:11 [🛤️ Spår 4]
🏁 Arrives Lund C 09:23

⏱️ Total: 38 min | 🔄 1 change

With delays:

🕐 **Depart 14:30** from Triangeln

🚂 Öresundståg 1042 → København H
⚠️ +8 min delay (expected 14:38 instead of 14:30)
🏁 Arrives ~15:25 (normally 15:17)

Walking Segment Details

CRITICAL: Always show walking details from the tool output:

  • Distance in meters (from line.distance)
  • Include walking in the "leave time" calculation
  • Show walking at start AND end of journey

Example tool output:

→ WALK 450m from Kalendegatan to Möllevångstorget

Format as:

🚶 Walk 450m to Möllevångstorget (~5 min)

Walk time estimate: ~100m per minute (normal walking speed)

Presenting Multiple Options

When showing journey options, make timing crystal clear:

I found 3 options for you:

**Option 1 - Leave now (09:00)** ✅ Recommended
🚶 5 min walk → 🚌 Bus 5 at 09:07 → arrives 09:25
⏱️ Total: 25 min

**Option 2 - Leave in 15m (09:15)**
🚶 5 min walk → 🚌 Bus 5 at 09:22 → arrives 09:40
⏱️ Total: 25 min

**Option 3 - Leave in 30m (09:30)**
🚶 5 min walk → 🚂 Train at 09:37 → arrives 09:48
⏱️ Total: 18 min | Faster but later departure

Time Offset Notation

Use clear notation for departure times:

NotationMeaning
"now"Immediately
"in 15m"15 minutes from now
"in 1h"1 hour from now
"at 14:30"Specific time

LLM Workflow: How to Plan a Trip

Follow this workflow when a user asks for a trip:

Step 1: Understand Time Intent

Parse what the user wants:

  • "How do I get to..." → Travel now
  • "I need to be there at 18:00" → Arrive mode
  • "Sometime around 3pm" → Query 14:30, show range
  • "In about an hour" → Calculate from current time

Step 2: Search for Both Locations

Search for origin and destination separately:

./search-location.sh "Malmö C"
./search-location.sh "Emporia"

Step 3: Validate Search Results

Check each result carefully:

  1. Exact or close match? - If the name matches what the user asked for, proceed.

  2. Multiple results returned? - The script shows up to 10 matches. If the first result isn't clearly correct, ask the user to confirm.

  3. Name significantly different? - If user asked for "the mall near Hyllie" and result shows "Emporia", confirm with user: "I found Emporia shopping center near Hyllie. Is this correct?"

  4. No results found? - Try alternative strategies (see below).

Step 4: Handle Ambiguous or Failed Searches

When results don't match or are ambiguous, ask clarifying questions:

I searched for "centrum" and found multiple locations:
1. Malmö Centrum (bus stop)
2. Lund Centrum (bus stop)
3. Helsingborg Centrum (bus stop)

Which one did you mean?

When no results are found, try these strategies:

  1. Try with city name for addresses:

    # If "Storgatan 10" fails, try:
    ./search-location.sh "Storgatan 10, Malmö"
    
  2. Try official station names:

    # If "Malmö station" fails, try:
    ./search-location.sh "Malmö C"
    
  3. Try landmark name only (without city):

    # If "Emporia, Malmö" fails, try:
    ./search-location.sh "Emporia"
    
  4. Use coordinates as last resort:

    • If you know the approximate location, use lat#lon format directly
    • Ask user: "I couldn't find that location. Can you provide the address or coordinates?"

Step 5: Convert Types for Journey API

The Journey API only accepts:

  • STOP_AREA - Bus/train stations (use ID directly)
  • LOCATION - GPS coordinates as lat#lon

If search returns ADDRESS or POI:

  • Use the coordinates from search result
  • Format as lat#lon with type LOCATION

Example:

# Search returns: ID: 123, Type: ADDRESS, Coordinates: 55.605, 13.003
# Use in journey as:
./journey.sh "55.605#13.003" LOCATION 9021012080000000 STOP_AREA

Step 6: Execute Journey Search

Once you have confirmed IDs/coordinates for both locations:

./journey.sh <from-id> <from-type> <to-id> <to-type> [datetime] [mode]

Step 7: Format Response with Emojis

Use the emoji guide above to present results clearly. Always use actual numbers from the tool output - never speculate or estimate.


Query Formatting Rules

The search API is sensitive to formatting. Follow these rules:

Landmarks and POIs: Name Only

Use the landmark name WITHOUT city name.

# CORRECT
./search-location.sh "Emporia"
./search-location.sh "Triangeln"
./search-location.sh "Turning Torso"

# WRONG - city name breaks POI search
./search-location.sh "Emporia, Malmö"        # May return wrong location!
./search-location.sh "Triangeln, Malmö"      # Unnecessary, may fail

Street Addresses: Include City

Include city name for better accuracy.

# CORRECT
./search-location.sh "Kalendegatan 12, Malmö"
./search-location.sh "Storgatan 25, Lund"
./search-location.sh "Drottninggatan 5, Helsingborg"

# RISKY - may be ambiguous
./search-location.sh "Kalendegatan 12"       # Works if unambiguous

Train Stations: Use Official Names

Use "C" suffix for central stations.

# CORRECT
./search-location.sh "Malmö C"
./search-location.sh "Lund C"
./search-location.sh "Helsingborg C"
./search-location.sh "Malmö Hyllie"
./search-location.sh "Malmö Triangeln"

# WRONG
./search-location.sh "Malmö"                 # Ambiguous!
./search-location.sh "Malmö Central"         # Not official name
./search-location.sh "Lund station"          # Not official name

Copenhagen (Cross-border)

Use Danish names or common alternatives.

# All work
./search-location.sh "København H"
./search-location.sh "Nørre

---

*Content truncated.*

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,4071,302

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,2201,024

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

9001,013

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

958658

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

970608

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,033496

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.