skanetrafiken
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.zipInstalls 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]
| Argument | Description |
|---|---|
query | Location name to search for |
limit | Number of results to show (default: 3, max: 10) |
Output includes:
ID- The location identifier (use this in journey search)Name- Official name of the locationType- STOP_AREA (station), ADDRESS, or POI (point of interest)Area- Region/municipalityCoordinates- 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]
| Argument | Description |
|---|---|
from-id | Origin location ID (from search) or coordinates (lat#lon) |
from-type | STOP_AREA, ADDRESS, POI, or LOCATION (for coordinates) |
to-id | Destination location ID or coordinates |
to-type | Type of destination |
datetime | Optional: "18:30", "tomorrow 09:00", "2026-01-15 09:00" |
mode | Optional: "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 Says | Intent | How to Query |
|---|---|---|
| "now", "next bus", "how do I get to" | Travel Now | No datetime parameter |
| "in 30 minutes", "in 1 hour", "after lunch" | Depart Later | Calculate time, use depart mode |
| "around 15:00", "sometime afternoon" | Around Time | Query with offset (see below) |
| "arrive by 18:00", "need to be there at 9" | Arrive By | Use arrive mode |
| "tomorrow morning", "on Friday at 10" | Future Time | Use 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 Says | Current: 14:00 | Query 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
| Emoji | Use 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:
- When to leave - The actual time user needs to start (including walking)
- Walking segments - Distance and time for any walking
- Transport departure - When the bus/train actually leaves
- Arrival time - When user reaches destination
- 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:
| Notation | Meaning |
|---|---|
| "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:
-
Exact or close match? - If the name matches what the user asked for, proceed.
-
Multiple results returned? - The script shows up to 10 matches. If the first result isn't clearly correct, ask the user to confirm.
-
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?"
-
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:
-
Try with city name for addresses:
# If "Storgatan 10" fails, try: ./search-location.sh "Storgatan 10, Malmö" -
Try official station names:
# If "Malmö station" fails, try: ./search-location.sh "Malmö C" -
Try landmark name only (without city):
# If "Emporia, Malmö" fails, try: ./search-location.sh "Emporia" -
Use coordinates as last resort:
- If you know the approximate location, use
lat#lonformat directly - Ask user: "I couldn't find that location. Can you provide the address or coordinates?"
- If you know the approximate location, use
Step 5: Convert Types for Journey API
The Journey API only accepts:
STOP_AREA- Bus/train stations (use ID directly)LOCATION- GPS coordinates aslat#lon
If search returns ADDRESS or POI:
- Use the coordinates from search result
- Format as
lat#lonwith typeLOCATION
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.*
More by openclaw
View all skills by openclaw →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.
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.
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."
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.
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.
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.
Related MCP Servers
Browse all serversGoogle Maps Travel Planner: Plan journeys, optimize itineraries, and get trip directions with AI-driven, automated trave
Access and analyze open government data, including budgets and crime stats, from Socrata gov datasets—no API key needed.
Boost Postgres performance with Postgres MCP Pro—AI-driven index tuning, health checks, and safe, intelligent SQL optimi
Access real-time web scraping with Bright Data. Scrape any website and extract structured data easily using advanced web
Powerful MCP server for Slack with advanced API, message fetching, webhooks, and enterprise features. Robust Slack data
Integrate Stripe for seamless payment processing, credit card payments, and customer management in e-commerce and billin
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.