Mapbox Google Maps Migration logo

Mapbox Google Maps Migration

Organization
mapbox
mapbox-google-maps-migration

Migration guide for developers moving from Google Maps Platform to Mapbox GL JS, covering API equivalents, pattern translations, and key differences

Overview

Publishermapbox
Repositorymapbox-agent-skills
Skill namemapbox-google-maps-migration
Stars
78
Forks
17
Bundled files
7
LicenseMIT
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Mapbox Google Maps Migration 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/mapbox/mapbox-agent-skills.git /tmp/mapbox-agent-skills
mkdir -p .claude/skills
cp -r /tmp/mapbox-agent-skills/skills/mapbox-google-maps-migration .claude/skills/mapbox-google-maps-migration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mapbox Google Maps Migration 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 Mapbox Google Maps Migration 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 Mapbox Google Maps Migration 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.

Mapbox Google Maps Migration Skill

Comprehensive guidance for migrating from Google Maps Platform to Mapbox GL JS. Provides API equivalents, pattern translations, and strategies for successful migration.

Core Philosophy Differences

Google Maps: Imperative & Object-Oriented

  • Create objects (Marker, Polygon, etc.)
  • Add to map with .setMap(map)
  • Update properties with setters
  • Heavy reliance on object instances

Mapbox GL JS: Declarative & Data-Driven

  • Add data sources
  • Define layers (visual representation)
  • Style with JSON
  • Update data, not object properties

Key Insight: Mapbox treats everything as data + styling, not individual objects.

Map Initialization

Google Maps

javascript
const map = new google.maps.Map(document.getElementById('map'), {
  center: { lat: 37.7749, lng: -122.4194 },
  zoom: 12,
  mapTypeId: 'roadmap' // or 'satellite', 'hybrid', 'terrain'
});

Mapbox GL JS

javascript
mapboxgl.accessToken = 'YOUR_MAPBOX_TOKEN';
const map = new mapboxgl.Map({
  container: 'map',
  style: 'mapbox://styles/mapbox/streets-v12', // or satellite-v9, outdoors-v12
  center: [-122.4194, 37.7749], // [lng, lat] - note the order!
  zoom: 12
});

Key Differences:

  • Coordinate order: Google uses {lat, lng}, Mapbox uses [lng, lat]
  • Authentication: Google uses API key in script tag, Mapbox uses access token in code
  • Styling: Google uses map types, Mapbox uses full style URLs

API Equivalents Reference

Map Methods

Google MapsMapbox GL JSNotes
map.setCenter(latLng)map.setCenter([lng, lat])Coordinate order reversed
map.getCenter()map.getCenter()Returns LngLat object
map.setZoom(zoom)map.setZoom(zoom)Same behavior
map.getZoom()map.getZoom()Same behavior
map.panTo(latLng)map.panTo([lng, lat])Animated pan
map.fitBounds(bounds)map.fitBounds([[lng,lat],[lng,lat]])Different bound format
map.setMapTypeId(type)map.setStyle(styleUrl)Completely different approach
map.getBounds()map.getBounds()Similar

Map Events

Google MapsMapbox GL JSNotes
google.maps.event.addListener(map, 'click', fn)map.on('click', fn)Simpler syntax
event.latLngevent.lngLatEvent property name
'center_changed''move' / 'moveend'Different event names
'zoom_changed''zoom' / 'zoomend'Different event names
'bounds_changed''moveend'No direct equivalent
'mousemove''mousemove'Same
'mouseout''mouseleave'Different name

Markers and Points

Simple Marker

Google Maps:

javascript
const marker = new google.maps.Marker({
  position: { lat: 37.7749, lng: -122.4194 },
  map: map,
  title: 'San Francisco',
  icon: 'custom-icon.png'
});

// Remove marker
marker.setMap(null);

Mapbox GL JS:

javascript
// Create marker
const marker = new mapboxgl.Marker()
  .setLngLat([-122.4194, 37.7749])
  .setPopup(new mapboxgl.Popup().setText('San Francisco'))
  .addTo(map);

// Remove marker
marker.remove();

Multiple Markers

Google Maps:

javascript
const markers = locations.map(
  (loc) =>
    new google.maps.Marker({
      position: { lat: loc.lat, lng: loc.lng },
      map: map
    })
);

Mapbox GL JS (Equivalent Approach):

javascript
// Same object-oriented approach
const markers = locations.map((loc) => new mapboxgl.Marker().setLngLat([loc.lng, loc.lat]).addTo(map));

Mapbox GL JS (Data-Driven Approach - Recommended for 100+ points):

javascript
// Add as GeoJSON source + layer (uses WebGL, not DOM)
map.addSource('points', {
  type: 'geojson',
  data: {
    type: 'FeatureCollection',
    features: locations.map((loc) => ({
      type: 'Feature',
      geometry: { type: 'Point', coordinates: [loc.lng, loc.lat] },
      properties: { name: loc.name }
    }))
  }
});

map.addLayer({
  id: 'points-layer',
  type: 'circle', // or 'symbol' for icons
  source: 'points',
  paint: {
    'circle-radius': 8,
    'circle-color': '#ff0000'
  }
});

Performance Advantage: Google Maps renders all markers as DOM elements (even when using the Data Layer), which becomes slow with 500+ markers. Mapbox's circle and symbol layers are rendered by WebGL, making them much faster for large datasets (1,000-10,000+ points). This is a significant advantage when building applications with many points.

Info Windows / Popups

Google Maps

javascript
const infowindow = new google.maps.InfoWindow({
  content: '<h3>Title</h3><p>Content</p>'
});

marker.addListener('click', () => {
  infowindow.open(map, marker);
});

Mapbox GL JS

javascript
// Option 1: Attach to marker
const marker = new mapboxgl.Marker()
  .setLngLat([-122.4194, 37.7749])
  .setPopup(new mapboxgl.Popup().setHTML('<h3>Title</h3><p>Content</p>'))
  .addTo(map);

// Option 2: On layer click (for data-driven markers)
map.on('click', 'points-layer', (e) => {
  const coordinates = e.features[0].geometry.coordinates.slice();
  const description = e.features[0].properties.description;

  new mapboxgl.Popup().setLngLat(coordinates).setHTML(description).addTo(map);
});

Migration Strategy

Step 1: Audit Current Implementation

Identify all Google Maps features you use:

  • Basic map with markers
  • Info windows/popups
  • Polygons/polylines
  • Geocoding
  • Directions
  • Clustering
  • Custom styling
  • Drawing tools
  • Street View (no Mapbox equivalent)
  • Other advanced features

Step 2: Set Up Mapbox

html
<!-- Replace Google Maps script -->
<script src="https://api.mapbox.com/mapbox-gl-js/v3.18.1/mapbox-gl.js"></script>
<link href="https://api.mapbox.com/mapbox-gl-js/v3.18.1/mapbox-gl.css" rel="stylesheet" />

Step 3: Convert Core Map

Start with basic map initialization:

  1. Replace new google.maps.Map() with new mapboxgl.Map()
  2. Fix coordinate order (lat,lng -> lng,lat)
  3. Update zoom/center

Step 4: Convert Features One by One

Prioritize by complexity:

  1. Easy: Map controls, basic markers
  2. Medium: Popups, polygons, lines
  3. Complex: Clustering, custom styling, data updates

Step 5: Update Event Handlers

Change event syntax:

  • google.maps.event.addListener() -> map.on()
  • Update event property names (latLng -> lngLat)

Step 6: Optimize for Mapbox

Take advantage of Mapbox features:

  • Convert multiple markers to data-driven layers
  • Use clustering (built-in)
  • Leverage vector tiles for custom styling
  • Use expressions for dynamic styling

Step 7: Test Thoroughly

  • Cross-browser testing
  • Mobile responsiveness
  • Performance with real data volumes
  • Touch/gesture interactions

Gotchas and Common Issues

Coordinate Order

javascript
// Google Maps
{ lat: 37.7749, lng: -122.4194 }

// Mapbox (REVERSED!)
[-122.4194, 37.7749]

Always double-check coordinate order!

Event Properties

javascript
// Google Maps
map.on('click', (e) => {
  console.log(e.latLng.lat(), e.latLng.lng());
});

// Mapbox
map.on('click', (e) => {
  console.log(e.lngLat.lat, e.lngLat.lng);
});

Timing Issues

javascript
// Google Maps - immediate
const marker = new google.maps.Marker({ map: map });

// Mapbox - wait for load
map.on('load', () => {
  map.addSource(...);
  map.addLayer(...);
});

Removing Features

javascript
// Google Maps
marker.setMap(null);

// Mapbox - must remove both
map.removeLayer('layer-id');
map.removeSource('source-id');

Updating Data Without Flash

Never remove and re-add layers to update data — this reinitializes WebGL resources and causes a visible flash. Instead:

javascript
// ✅ Update data in place (no flash)
map.getSource('stores').setData(newGeoJSON);

// ✅ Filter existing data (GPU-side, fastest)
map.setFilter('stores-layer', ['==', ['get', 'category'], 'coffee']);

// ❌ BAD: remove + re-add causes flash
map.removeLayer('stores-layer');
map.removeSource('stores');
map.addSource('stores', { ... });
map.addLayer({ ... });

When NOT to Migrate

Consider staying with Google Maps if:

  • Street View is critical - Mapbox doesn't have equivalent
  • Tight Google Workspace integration - Places API deeply integrated
  • Already heavily optimized - Migration cost > benefits
  • Team expertise - Retraining costs too high
  • Short-term project - Not worth migration effort

Quick Reference: Side-by-Side Comparison

javascript
// GOOGLE MAPS
const map = new google.maps.Map(el, {
  center: { lat: 37.7749, lng: -122.4194 },
  zoom: 12
});

const marker = new google.maps.Marker({
  position: { lat: 37.7749, lng: -122.4194 },
  map: map
});

google.maps.event.addListener(map, 'click', (e) => {
  console.log(e.latLng.lat(), e.latLng.lng());
});

// MAPBOX GL JS
mapboxgl.accessToken = 'YOUR_TOKEN';
const map = new mapboxgl.Map({
  container: el,
  center: [-122.4194, 37.7749], // REVERSED!
  zoom: 12,
  style: 'mapbox://styles/mapbox/streets-v12'
});

const marker = new mapboxgl.Marker()
  .setLngLat([-122.4194, 37.7749]) // REVERSED!
  .addTo(map);

map.on('click', (e) => {
  console.log(e.lngLat.lat, e.lngLat.lng);
});

Remember: lng, lat order in Mapbox!

Additional Resources

Integration with Other Skills

Works with:

  • mapbox-web-integration-patterns: Framework-specific migration guidance
  • mapbox-web-performance-patterns: Optimize after migration
  • mapbox-token-security: Secure your Mapbox tokens properly
  • mapbox-geospatial-operations: Use Mapbox's geospatial tools effectively
  • mapbox-search-patterns: Migrate geocoding/search functionality

Reference Files

The following reference files contain detailed migration guides for specific topics. Load them when working on those areas:

  • references/shapes-geocoding.md — Polygons, Polylines, Custom Icons, Geocoding
  • references/directions-controls.md — Directions/Routing, Controls
  • references/clustering-styling.md — Clustering, Styling/Appearance
  • references/data-performance.md — Data Updates, Performance, Common Migration Patterns (Store Locator, Drawing Tools, Heatmaps)
  • references/api-services.md — API Services Comparison, Pricing, Plugins, Framework Integration, Testing, Migration Checklist

To load a reference, read the file relative to this skill directory, e.g.:

Load references/shapes-geocoding.md

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 Mapbox Google Maps Migration AI skill do?

Migration guide for developers moving from Google Maps Platform to Mapbox GL JS, covering API equivalents, pattern translations, and key differences

Why use Mapbox Google Maps Migration on TypingMind?

Because you install it once and use it with any model. Mapbox Google Maps Migration 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 Mapbox Google Maps Migration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mapbox/mapbox-agent-skills/tree/main/skills/mapbox-google-maps-migration. 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 Mapbox Google Maps Migration?

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 Mapbox Google Maps Migration?

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

Is the Mapbox Google Maps Migration AI skill free?

Yes. It is published on GitHub by mapbox under the MIT 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 👇