Mapbox Cartography logo

Mapbox Cartography

Organization
mapbox
mapbox-cartography

Expert guidance on map design principles, color theory, visual hierarchy, typography, and cartographic best practices for creating effective and beautiful maps with Mapbox. Use when designing map styles, choosing colors, or making cartographic decisions.

Overview

Publishermapbox
Repositorymapbox-agent-skills
Skill namemapbox-cartography
Stars
78
Forks
17
Bundled files
4
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.

  • 4 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 Cartography 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-cartography .claude/skills/mapbox-cartography
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mapbox Cartography 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 Cartography 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 Cartography 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 Cartography Skill

This skill provides expert cartographic knowledge to help you design effective, beautiful, and functional maps using Mapbox.

Core Cartographic Principles

Visual Hierarchy

Maps must guide the viewer's attention to what matters most:

  • Most important: POIs, user location, route highlights
  • Secondary: Major roads, city labels, landmarks
  • Tertiary: Minor streets, administrative boundaries
  • Background: Water, land use, terrain

Implementation:

  • Use size, color intensity, and contrast to establish hierarchy
  • Primary features: high contrast, larger symbols, bold colors
  • Background features: low contrast, muted colors, smaller text

Color Theory for Maps

Color Harmony:

  • Analogous colors: Use colors next to each other on color wheel (blue-green-teal) for cohesive designs
  • Complementary colors: Use opposite colors (blue/orange, red/green) for high contrast emphasis
  • Monochromatic: Single hue with varying saturation/brightness for elegant, minimal designs

Color Psychology:

  • Blue: Water, trust, calm, professional (default for water bodies)
  • Green: Parks, nature, growth, eco-friendly (vegetation, parks)
  • Red/Orange: Urgent, important, dining (alerts, restaurants)
  • Yellow: Caution, highlight, attention (warnings, selected items)
  • Gray: Neutral, background, roads (infrastructure)

Accessibility:

  • Ensure 4.5:1 contrast ratio for text (WCAG AA)
  • Don't rely solely on color to convey information
  • Test designs with colorblind simulators
  • Avoid red/green combinations for critical distinctions

Color Palette Templates:

Light Theme (Day/Professional):

json
{
  "background": "#f5f5f5",
  "water": "#a0c8f0",
  "parks": "#d4e7c5",
  "roads": "#ffffff",
  "buildings": "#e0e0e0",
  "text": "#333333"
}

Dark Theme (Night Mode):

json
{
  "background": "#1a1a1a",
  "water": "#0d47a1",
  "parks": "#2e7d32",
  "roads": "#3a3a3a",
  "buildings": "#2d2d2d",
  "text": "#ffffff"
}

Road color rule for dark themes: Roads must use neutral dark gray (#3a3a3a), visibly distinct from the background but not colored. Never style roads with amber, blue, or other hues — reserve color for app data layers (routes, markers). Colored base roads and colored data layers will compete visually. Local roads that blend into the background (#1e1e1e on #1a1a1a) create a "floating labels" problem where street names appear with no visible road beneath them.

High Contrast (Accessibility):

json
{
  "background": "#000000",
  "water": "#0066ff",
  "parks": "#00ff00",
  "roads": "#ffffff",
  "buildings": "#808080",
  "text": "#ffffff"
}

Vintage/Retro:

json
{
  "background": "#f4e8d0",
  "water": "#b8d4d4",
  "parks": "#c8d4a4",
  "roads": "#d4c4a8",
  "buildings": "#e4d4c4",
  "text": "#4a3828"
}

Typography at Map Scale

Font Selection:

  • Sans-serif (Roboto, Open Sans): Modern, clean, high legibility at small sizes - use for labels
  • Serif (Noto Serif): Traditional, formal - use sparingly for titles or historic maps
  • Monospace: Technical data, coordinates

Text Sizing:

Place labels (cities, POIs): 11-14px
Street labels: 9-11px
Feature labels (parks): 10-12px
Map title: 16-20px
Attribution: 8-9px

Label Placement:

  • Point labels: Center or slightly offset (avoid overlap with symbol)
  • Line labels: Follow line curve, repeat for long features
  • Area labels: Center in polygon, sized appropriately
  • Prioritize: Major features get labels first, minor features labeled if space allows

Zoom Level Strategy

Zoom 0-4 (World to Continent):

  • Major country boundaries
  • Ocean and sea labels
  • Capital cities only

Zoom 5-8 (Country to State):

  • State/province boundaries
  • Major cities
  • Major highways
  • Large water bodies

Zoom 9-11 (Metro Area):

  • City boundaries
  • Neighborhoods
  • All highways and major roads
  • Parks and landmarks

Zoom 12-15 (Neighborhood):

  • All streets
  • Building footprints
  • POIs (restaurants, shops)
  • Street names

Note: Mapbox's hosted Streets style defaults to showing most POIs around zoom 14. For custom styles, start POIs at zoom 12 — this is the neighborhood scale where density is manageable and users are browsing. Zoom 14 is late; zoom 10 (metro-area scale) is far too early and creates severe icon clutter.

Zoom 16-22 (Street Level):

  • All detail
  • House numbers
  • Parking lots
  • Fine-grained POIs

Mapbox-Specific Implementation Guidance

Style Layer Best Practices

Layer Ordering (bottom to top):

  1. Background (solid color or pattern)
  2. Landuse (parks, residential, commercial)
  3. Water bodies (oceans, lakes, rivers)
  4. Terrain/hillshade (if using elevation)
  5. Buildings (3D or 2D footprints)
  6. Roads (highways → local streets)
  7. Borders (country, state lines)
  8. Labels (place names, street names)
  9. POI symbols
  10. User-generated content (routes, markers)

Common mistake: Developers often put their app's route line or active markers below POI symbols, reasoning that "POIs must stay visible." This is backwards — user-generated content (your route, selected location, user position) is the most important layer and must render above everything, including POIs. A route line that covers a POI icon is acceptable; a route obscured by POI icons is not.

Map Context Considerations

Know Your Audience:

  • General public: Simplify, use familiar patterns (Google/Apple style)
  • Technical users: Include more detail, technical layers, data precision
  • Domain experts: Show specialized data, use domain-specific symbology

Platform Considerations:

  • Mobile: Larger touch targets (44x44px minimum), simpler designs, readable at arm's length
  • Desktop: Can include more detail, hover interactions, complex overlays
  • Print: Higher contrast, larger text, consider CMYK color space
  • Outdoor/Bright: Higher contrast, avoid subtle grays

Use Case Optimization:

  • Navigation: Emphasize roads, clear hierarchy, route visibility
  • Data visualization: Muted base map, let data stand out
  • Storytelling: Guide viewer attention, establish mood with colors
  • Location selection: Show POIs clearly, provide context
  • Analysis: Include relevant layers, maintain clarity at different zooms

Reference Files

For detailed guidance on specific topics, load these references as needed:

  • references/scenarios.md — Common scenario guidance (Restaurant Finder, Real Estate, Data Visualization, Navigation)
  • references/performance-testing.md — Performance optimization, testing checklist, and common mistakes to avoid

When to Use This Skill

Invoke this skill when:

  • Designing a new map style
  • Choosing colors for map elements
  • Making decisions about visual hierarchy
  • Optimizing for specific use cases
  • Troubleshooting visibility issues
  • Ensuring accessibility
  • Creating themed maps (dark mode, vintage, etc.)

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 Cartography AI skill do?

Expert guidance on map design principles, color theory, visual hierarchy, typography, and cartographic best practices for creating effective and beautiful maps with Mapbox. Use when designing map styles, choosing colors, or making cartographic decisions.

Why use Mapbox Cartography on TypingMind?

Because you install it once and use it with any model. Mapbox Cartography 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 Cartography in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mapbox/mapbox-agent-skills/tree/main/skills/mapbox-cartography. 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 Cartography?

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 Cartography?

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

Is the Mapbox Cartography 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 👇