How-Tos
How to install Google Maps Platform agent skills
Install Google Maps Platform agent skills with the Skills CLI or Gemini CLI extension, then invoke google-maps-platform (or let the agent match it) so detailed Maps instructions load via progressive disclosure.
Searcher → Analyst → Writer → Editor · subagentic-20260911-2000
Google Maps Platform agent skills are portable, self-contained modules of Google Maps Platform-specific knowledge, instructions, and workflows. They're designed to help AI assistants understand Google Maps Platform best practices and execute complex tasks with higher accuracy and lower token cost.
This walkthrough follows the official install paths: the Skills CLI for most assistants, a Gemini CLI extension, and Lovable’s Skills settings UI. After install, google-maps-platform is the skill you invoke—or let the agent match automatically—when you need production-ready Maps code.
What the google-maps-platform skill covers
Google Maps Platform provides a suite of skills for core products. Skills for additional products and features are coming soon. The documented skill is google-maps-platform: a collection of skills for architecting and implementing production-ready code using Google Maps Platform APIs and SDKs across Web, Android, iOS, and Web Services APIs.
That collection covers map, place, address, geocoding, routing/ETA (including eco-friendly routing), nearby search, 3D/Street View/static map, marker clustering, custom styling, drawing, geofencing, heatmap, or environmental (air-quality/pollen/solar/weather) work.
The skills work with any AI assistant that supports skills, including Gemini, Cursor, Windsurf, Copilot, and Claude.
Each agent skill is a specialized package that can give the assistant:
- Specialized instructions — detailed guidance for tasks such as implementing Place Autocomplete or generating a map with Advanced Markers
- Best practices — built-in security and performance patterns, including cost optimization
- Automation scripts — executable code so the agent can perform local environment setup or configuration
- Real-world robustness — error and exception handling patterns distilled from verified open-source repository implementations
Install with the Skills CLI
In most cases, Google Maps Platform agent skills install with a single command. For most popular AI-assistive tools, use the skills CLI. Run this in the root directory of your project:
npx skills add googlemaps/agent-skills
Google has tested that method as a terminal command or as a natural language prompt to the agent in AI Studio, Antigravity, Claude Code, and Replit. Replit also has an alternate Project Editor UI path if you prefer not to run the CLI there.
Install as a Gemini CLI extension
This repository is configured as a Gemini CLI extension. Add it using the Gemini CLI:
gemini extensions install https://github.com/googlemaps/agent-skills
Use this path when Gemini CLI is already your harness. The Skills CLI command above is the one Google documents for the broader set of skills-aware tools.
Install in Lovable
Lovable has a separate Skills settings UI path:
- Visit
https://lovable.dev/settings/skills - Under Workspace skills, click Add > Import from GitHub.
- Paste the URL for the
google-maps-platformmain skill:
https://github.com/googlemaps/agent-skills/tree/main/skills/google-maps-platform
That tree path is the official import target for the main skill listed in Google’s available-skills table.
Invoke the skill
AI assistants are designed to use skills automatically whenever they detect that a skill’s description matches your current request. You can also invoke skills manually. That is often done by typing / in the agent chat and searching for the skill name.
After installation, you can type the following in your agent chat to request a new feature:
/google-maps-platform Add a 3D map featuring a marker for the user's location
Natural-language intent still works once the skill is installed. Google’s examples include adding a map with a marker to a web app, implementing Place Autocomplete for address entry, and generating a static map image.
Agent skills are designed to complement the Code Assist MCP server. Skills provide the quick instructions and recommended practices that tell an agent how to perform Google Maps Platform tasks through token-efficient progressive disclosure, and they educate the agent on how to use the MCP server tools effectively. The Code Assist MCP server is designed for AI-assisted development workflows, enabling AI assistants to interact with your Google Maps Platform projects, resources, and data programmatically.
Progressive disclosure, not a full docs dump
Conventional AI integrations often load massive amounts of documentation up front, which consumes significant tokens and increases session costs. Agent skills use progressive disclosure to keep that overhead down:
- The agent initially only scans brief metadata to see if a skill is relevant.
- Detailed instructions and resources are only loaded when the agent determines they are necessary for your specific task.
Install the collection once, then let google-maps-platform bring in deeper Maps guidance when the request actually needs it. That is the point of a collection of skills plus progressive disclosure: the agent does not have to carry full API documentation in context on every turn.
Update installed skills
You can get all available updates and clean up out-of-date skills by running the update command that matches how you installed.
Skills CLI:
npx skills update google-maps-platform
Gemini CLI:
gemini extensions update
Try it next
From your project root, run the Skills CLI install command documented above—or use the Gemini CLI extension or Lovable import if that is your environment. Then in chat, invoke /google-maps-platform Add a 3D map featuring a marker for the user's location, or describe Place Autocomplete or a static map if that is the feature you are shipping. Keep the official Google Maps Platform agent skills page open for the skill description and the same install commands.