Agent skills
An agent skill is a packaged set of instructions and reference material loaded straight into an AI agent's context. These skills teach agents how to reason about geospatial work — writing performant PostGIS queries, structuring spatial schemas, or driving GDAL and QGIS — without running a separate server.
Read the skills FAQarrow_forwardNo approved agent skills match the current filters yet.
filter_alt_offClear filtersAn agent skill is a packaged set of instructions and reference material loaded directly into an AI agent's context. It teaches the agent how to approach a task — for example, writing performant PostGIS queries or structuring a spatial schema — without running a separate process.
An MCP server is a running program the agent connects to over a transport such as stdio or HTTP; it exposes callable tools. An agent skill is static knowledge loaded into the agent's context — no process, no transport. A skill shapes how the agent reasons; an MCP server gives the agent new actions to call.
Each skill's detail page shows a single copyable install line — typically a command that adds the skill from its source repository to your agent. There is no archive to download; the skill is pulled directly from its repository.