> For the complete documentation index, see [llms.txt](https://docs.carto.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.carto.com/carto-for-agents/agent-skills.md). # CARTO Agent Skills **CARTO Agent Skills** is a public catalog of short, on-demand playbooks that teach AI coding agents how to drive the CARTO platform fluently. The repository is at [`CartoDB/agent-skills`](https://github.com/CartoDB/agent-skills) on GitHub. ## Why agent skills? Generic LLMs know *about* CARTO but make small mistakes when actually driving it: the wrong tool for the job, an outdated SQL dialect, a missing async-job handshake, the wrong import shape for a tileset. Each skill is a focused playbook the agent loads on demand when a request matches its domain, so the agent ships idiomatic, working CARTO output the first time. The skills route the agent to the **right access path** for each task. For most work — exploring data, creating and editing maps, building and running Workflows — that path is the [CARTO MCP Server](/carto-for-agents/mcp-server.md), which the agent calls inline. The skills reach for the [CARTO CLI](/carto-for-agents/cli.md) when a task calls for scripting, CI/CD, headless runs, bulk and cross-organization operations, or deeper administration and auditing (such as querying usage logs). You don't choose; the skill picks based on what you're asking for and what's available. ## Three tiers The catalog is organized in three layered tiers. An agent routes to the right skill automatically based on user intent. * **Utility**. Foundational CARTO primitives (setup, connect, query, explore). Loaded by other skills as a shared base. * **Platform**. CARTO product surfaces (workflows, Builder maps, imports, Data Observatory, org admin). Build on the utility tier. * **Use-case patterns**. Recipe skills that compose platform skills into end-to-end spatial analyses (hotspot analysis, site selection, trade areas, GWR). Each carries trigger keywords so the agent routes on user intent. For the full catalog with descriptions and trigger keywords, see [Skills catalog](/carto-for-agents/agent-skills/skills-catalog.md). For the layering rationale, see [`ARCHITECTURE.md`](https://github.com/CartoDB/agent-skills/blob/master/ARCHITECTURE.md) in the repo. ## Installing the skills The catalog ships ready-made install manifests for **Claude Code, Codex, Gemini CLI, and the Skills CLI** today, all from the same upstream source. Any other coding agent that supports a compatible plugin or rules mechanism can consume the same catalog. See [Installation](/carto-for-agents/agent-skills/installation.md) for the per-agent commands, and [Connect your platform](/carto-for-agents/connect-your-platform.md) to set up CARTO end to end in your agent. ## How it composes with the rest of CARTO for Agents * The skills route to the [**CARTO MCP Server**](/carto-for-agents/mcp-server.md) for inline, in-conversation work — exploring connections, creating and editing maps, building and running Workflows, and running SQL. Connect the MCP Server so these tools are available in your agent. * They reach for the [**CARTO CLI**](/carto-for-agents/cli.md) when a task calls for scripting, CI/CD, headless runs, bulk or cross-organization operations, deeper administration and auditing (like SQL over usage logs), or the fullest command surface. Skills that need the CLI say so and walk first-time users through install and login (`carto-basics`). * As you publish Workflows as MCP tools, the same Workflows become callable through the MCP Server, and the skills know to use them. ## Source of truth This documentation summarizes the catalog as it ships today. The canonical, always-up-to-date source is the public repo at [`CartoDB/agent-skills`](https://github.com/CartoDB/agent-skills), specifically `skills/catalog.json`, which lists every shipped skill, its tier, its dependencies, and its description. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.carto.com/carto-for-agents/agent-skills.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.