Mapbox Style Quality logo

Mapbox Style Quality

Organization
mapbox
mapbox-style-quality

Expert guidance on validating, optimizing, and ensuring quality of Mapbox styles through validation, accessibility checks, and optimization. Use when preparing styles for production, debugging issues, or ensuring map quality standards.

Overview

Publishermapbox
Repositorymapbox-agent-skills
Skill namemapbox-style-quality
Stars
78
Forks
17
Bundled files
5
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.

  • 5 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 Style Quality 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-style-quality .claude/skills/mapbox-style-quality
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mapbox Style Quality 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 Style Quality 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 Style Quality 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 Style Quality Skill

This skill provides expert guidance on ensuring Mapbox style quality through validation, accessibility, and optimization tools.

When to Use Quality Tools

Pre-Production Checklist

Before deploying any Mapbox style to production:

  1. Validate all expressions - Catch syntax errors before runtime
  2. Check color contrast - Ensure text is readable (WCAG compliance)
  3. Validate GeoJSON sources - Ensure data integrity
  4. Optimize style - Reduce file size and improve performance
  5. Compare versions - Understand what changed
  6. Remove empty layers - Delete layers with no visible paint properties as a final cleanup step
  7. Simplify redundant boolean expressions - Clean up filters with unnecessary boolean logic (e.g., ["all", expr]expr, ["any", false, expr]expr)

During Development

When adding GeoJSON data:

  • Always validate external GeoJSON with validate_geojson_tool before using as a source

When writing expressions:

  • Validate expressions with validate_expression_tool as you write them
  • Catch type mismatches early (e.g., using string operator on number)
  • Verify operator availability in your Mapbox GL JS version
  • Test expressions with expected data types

When styling text/labels:

  • Check foreground/background contrast with check_color_contrast_tool
  • Aim for WCAG AA minimum (4.5:1 for normal text, 3:1 for large text)
  • Use AAA standard (7:1 for normal text) for better accessibility
  • Consider different background scenarios (map tiles, overlays)

Before Committing Changes

Compare style versions:

  • Use compare_styles_tool to generate a diff report
  • Review all layer changes, source modifications, and expression updates
  • Understand the impact of your changes
  • Document significant changes in commit messages

Before Deployment

Optimize the style:

  • Run optimize_style_tool to reduce file size
  • Remove unused sources that reference deleted layers
  • Eliminate duplicate layers with identical properties
  • Simplify redundant boolean expressions in filters (e.g., collapse ["all", expr] to expr, remove tautological conditions)
  • Remove empty layers (layers with no visible paint properties) as a final cleanup step

Validation Best Practices

GeoJSON Validation

Always validate when:

  • Loading GeoJSON from user uploads
  • Fetching GeoJSON from external APIs
  • Processing GeoJSON from third-party sources
  • Converting between data formats

Common GeoJSON errors:

  • Invalid coordinate ranges (longitude > 180 or < -180)
  • Unclosed polygon rings (first and last coordinates must match)
  • Wrong coordinate order (should be [longitude, latitude], not [latitude, longitude])
  • Missing required properties (type, coordinates, geometry)
  • Invalid geometry types or nesting

Example workflow:

1. Receive GeoJSON data
2. Validate with validate_geojson_tool
3. If valid: Add as source to style
4. If invalid: Fix errors, re-validate

Expression Validation

Validate expressions for:

  • Filter conditions (filter property on layers)
  • Data-driven styling (paint and layout properties)
  • Feature state expressions
  • Dynamic property calculations

Common expression errors:

  • Type mismatches (string operators on numbers)
  • Invalid operator names or wrong syntax
  • Wrong number of arguments for operators
  • Nested expression errors
  • Using unavailable operators for your GL JS version

Prevention strategies:

  • Validate as you write expressions, not at runtime
  • Test expressions with representative data
  • Use type checking (expectedType parameter)
  • Validate in context (layer, filter, paint, layout)

Accessibility Validation

WCAG Levels:

  • AA (minimum): 4.5:1 for normal text, 3:1 for large text
  • AAA (enhanced): 7:1 for normal text, 4.5:1 for large text

Text size categories:

  • Normal: < 18pt or < 14pt bold
  • Large: ≥ 18pt or ≥ 14pt bold

Common scenarios to check:

  • Text labels on map tiles
  • POI labels with background colors
  • Custom markers with text
  • UI overlays on maps
  • Legend text and symbols
  • Attribution text

Testing strategy:

  • Test against both light and dark map tiles
  • Consider overlay backgrounds (popups, modals)
  • Test in different lighting conditions (mobile outdoor use)
  • Verify contrast at different zoom levels

Quality Workflow Examples

Basic Quality Check

1. Validate expressions in style
2. Check color contrast for text layers
3. Optimize if needed

Full Pre-Production Workflow

1. Validate all GeoJSON sources
2. Validate all expressions (filters, paint, layout)
3. Check color contrast for all text layers
4. Compare with previous production version
5. Optimize style
6. Test optimized style
7. Deploy

Troubleshooting Workflow

1. Compare working vs. broken style
2. Identify differences
3. Validate suspicious expressions
4. Check GeoJSON data if source-related
5. Verify color contrast if visibility issue

Common Issues and Solutions

Runtime Expression Errors

Problem: Map throws expression errors at runtime Solution: Validate expressions with validate_expression_tool during development Prevention: Add expression validation to pre-commit hooks or CI/CD

Poor Text Readability

Problem: Text labels are hard to read on map Solution: Check contrast with check_color_contrast_tool, adjust colors to meet WCAG AA Prevention: Test text on both light and dark backgrounds, check at different zoom levels

Large Style File Size

Problem: Style takes long to load or transfer Solution: Run optimize_style_tool to remove redundancies and simplify Prevention: Regularly optimize during development, remove unused sources immediately

Invalid GeoJSON Source

Problem: GeoJSON source fails to load or render Solution: Validate with validate_geojson_tool, fix coordinate issues, verify structure Prevention: Validate all external GeoJSON before adding to style

Unexpected Style Changes

Problem: Style changed but unsure what modified Solution: Use compare_styles_tool to generate diff report Prevention: Compare before/after for all significant changes, document modifications

Tool Quick Reference

ToolUse WhenOutput
validate_geojson_toolAdding GeoJSON sourcesValid/invalid + error list
validate_expression_toolWriting expressionsValid/invalid + error list
check_color_contrast_toolStyling text labelsPasses/fails + WCAG levels
compare_styles_toolReviewing changesDiff report with paths
optimize_style_toolBefore deploymentOptimized style + savings

Reference Files

For detailed guidance on specific topics, load the relevant reference:

  • references/optimization.md — Optimization types, strategies, recommended order, and maintenance best practices
  • references/comparison.md — Style comparison workflows, ignoreMetadata usage, and refactoring workflow
  • references/ci-integration.md — Git pre-commit hooks, CI/CD pipeline steps, and code review checklist

Load instruction: Read the reference file when the user needs in-depth guidance on that topic.

Additional Resources

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 Style Quality AI skill do?

Expert guidance on validating, optimizing, and ensuring quality of Mapbox styles through validation, accessibility checks, and optimization. Use when preparing styles for production, debugging issues, or ensuring map quality standards.

Why use Mapbox Style Quality on TypingMind?

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

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

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 Style Quality?

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

Is the Mapbox Style Quality 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 👇