tabussen

1
1
Source

Västerbotten & Umeå public transport trip planner (Tabussen/Ultra). Plans bus journeys using ResRobot API. Supports stops, addresses, coordinates, regional and local routes throughout Västerbotten county.

Install

mkdir -p .claude/skills/tabussen && curl -L -o skill.zip "https://mcp.directory/api/skills/download/4354" && unzip -o skill.zip -d .claude/skills/tabussen && rm skill.zip

Installs to .claude/skills/tabussen

About this skill

Tabussen Trip Planner

Plan public transport journeys in Västerbotten, Sweden - including Umeå local traffic (Ultra) and regional routes (Länstrafiken Västerbotten).

Overview

This skill uses the ResRobot API (Trafiklab) to provide journey planning for Tabussen/Ultra. ResRobot is Sweden's national public transport API covering all operators including Länstrafiken Västerbotten.

Coverage:

  • Ultra (Umeå local bus traffic)
  • Länstrafiken Västerbotten (regional buses)
  • Connections to/from other Swedish regions
  • Train connections where applicable

Commands

1. Search Location

Search for stops, stations, or points of interest.

./search-location.sh <query> [limit]
ArgumentDescription
queryLocation name to search for (append ? for fuzzy search)
limitNumber of results to show (default: 5, max: 10)

Output includes:

  • ID - The stop identifier (use this in journey search)
  • Name - Official name of the stop
  • Coordinates - Latitude, longitude
  • Weight - Traffic volume indicator (higher = more traffic)

Search tips:

  • Use ? suffix for fuzzy/partial matching: "Vasaplan?"
  • Exact search without ?: "Vasaplan"
  • Include municipality for precision: "Umeå Vasaplan"

2. Journey Search

Plan a journey between two locations using their IDs.

./journey.sh <from-id> <to-id> [datetime] [mode]
ArgumentDescription
from-idOrigin stop ID (from search)
to-idDestination stop ID
datetimeOptional: "18:30", "tomorrow 09:00", "2026-01-28 14:00"
modeOptional: "depart" (default) or "arrive"

Coordinate-based search:

./journey.sh "63.825#20.263" <to-id> [datetime] [mode]

Use lat#lon format for coordinates (WGS84 decimal degrees).


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"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
busBus (Tabussen/Ultra)
trainTrain
walkWalking segment
clockTime/duration
clock1Departure time
goalArrival time
pinStop/station
houseOrigin (home/start)
targetDestination
warningDelay or disruption
checkOn time
arrows_counterclockwiseTransfer/change

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 actually leaves
  4. Arrival time - When user reaches destination
  5. Line number and direction - Which bus to take

Example Response Format

For a simple direct journey:

**Leave now** from Vasaplan

**Vasaplan** -> **Universitetet**
Bus 1 (mot Mariehem) departs 09:07
Arrives 09:18 at Universitetet

Total: 11 min

For a journey with transfer:

**Leave at 08:45**

Walk 300m to Vasaplan (~4 min)

**Vasaplan** -> **Umeå C** -> **Skellefteå**

**Leg 1:**
Bus 1 departs 08:51
Arrives Umeå C 09:05

Transfer at Umeå C (15 min)

**Leg 2:**
Bus 100 (mot Skellefteå) departs 09:20
Arrives Skellefteå busstation 11:45

Total: 3h | 1 change

Walking Segment Details

Always show walking details:

  • Distance in meters
  • Include walking in the "leave time" calculation
  • 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
Walk 5 min -> Bus 1 at 09:07 -> arrives 09:25
Total: 25 min

**Option 2 - Leave in 15m (09:15)**
Walk 5 min -> Bus 1 at 09:22 -> arrives 09:40
Total: 25 min

**Option 3 - Leave in 30m (09:30)**
Walk 5 min -> Bus 8 at 09:37 -> arrives 09:48
Total: 18 min | Faster but later departure

Which works best for you?

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 "Vasaplan?"
./search-location.sh "Universitetet?"

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 "university" and result shows "Umeå Universitet", confirm with user.

  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. Umeå Vasaplan (central bus hub)
2. Skellefteå centrum
3. Lycksele centrum

Which one did you mean?

When no results are found, try these strategies:

  1. Try with city name:

    # If "Storgatan 10" fails, try:
    ./search-location.sh "Storgatan 10, Umeå?"
    
  2. Try common variations:

    # "Universitetet" -> "Umeå universitet"
    # "Sjukhuset" -> "NUS" or "Norrlands universitetssjukhus"
    
  3. Use fuzzy search (add ?):

    ./search-location.sh "univ?"
    

Step 5: Execute Journey Search

Once you have confirmed IDs for both locations:

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

Step 6: Format Response

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


Query Formatting Rules

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

Common Stop Names in Umeå

User SaysSearch For
"Vasaplan", "centrum""Umeå Vasaplan?"
"Universitetet", "uni""Umeå universitet?"
"NUS", "sjukhuset""Norrlands universitetssjukhus?"
"Ikea""IKEA Umeå?"
"Flygplatsen""Umeå Airport?"
"Järnvägsstationen", "tåget""Umeå centralstation?"

Regional Destinations

DestinationSearch For
Skellefteå"Skellefteå busstation?"
Lycksele"Lycksele busstation?"
Vindeln"Vindeln station?"
Robertsfors"Robertsfors centrum?"
Holmsund"Holmsund centrum?"

Street Addresses

Include city name for better accuracy:

./search-location.sh "Storgatan 25, Umeå?"
./search-location.sh "Kungsgatan 10, Skellefteå?"

Examples

Example 1: Travel Now (Umeå Local)

User: "How do I get from Vasaplan to NUS?"

./search-location.sh "Umeå Vasaplan"
./search-location.sh "NUS?"
./journey.sh 740020116 740023840

Response:

**Leave now** from Vasaplan

**Vasaplan** -> **Universitetssjukhuset**
Bus 8 (mot Lyktvägen) departs 11:01
Arrives 11:06

Total: 5 min | Direct, no changes

Example 2: Regional Journey

User: "I need to get to Skellefteå from Umeå tomorrow at 8"

./search-location.sh "Umeå Vasaplan"
./search-location.sh "Skellefteå?"
./journey.sh 740020116 740000053 "tomorrow 08:00"

Response:

**Depart tomorrow at 08:04** from Vasaplan

Walk 766m to Umeå Busstation (~11 min)

**Umeå Busstation** -> **Skellefteå busstation**
Bus 20 (Länstrafik mot Haparanda) departs 08:15
Arrives 10:40 at Skellefteå busstation

Total: 2h 36min | Direct (with walk)

Example 3: Arrive By Time

User: "I need to be at NUS by 08:00 tomorrow"

./search-location.sh "Umeå Vasaplan"
./search-location.sh "NUS?"
./journey.sh 740020116 740023840 "tomorrow 08:00" arrive

Response:

**Arrive by 08:00** at NUS

**Vasaplan** -> **Universitetssjukhuset**
Bus 9 departs **07:51**
Arrives **07:56** - 4 min buffer

Leave Vasaplan by 07:51 to arrive on time!

Example 4: From Address/Coordinates

User: "I'm at Storgatan 50 in Umeå, how do I get to IKEA?"

./search-location.sh "Storgatan 50, Umeå?"
# If no result, use coordinates
./journey.sh "63.826#20.263" 740066123

DateTime Formats

All times are Swedish local time (CET/CEST).

FormatExampleMeaning
(empty)Travel now
HH:MM"08:30"Today at 08:30
tomorrow HH:MM"tomorrow 09:00"Tomorrow at 09:00
YYYY-MM-DD HH:MM"2026-01-28 14:00"Specific date

Output Forma


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.

1,6851,428

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."

1,2641,326

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.

1,5351,147

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.

1,355809

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.

1,264728

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.

1,488684