- Home
- Skills
- Data & Databases
- open map stack
More screenshots
Works with the AI Agents you already use
open map stack
Build and execute production-grade, reproducible geospatial pipelines using cloud-native tools like DuckDB and PMTiles.
$19.90
open map stack
Example session with this skill installed
How accessible are green recreational areas to buildings in Tallinn, Estonia? Are there areas which are NOT within walking distance? Make me an interactive web map as result.
- Read your context and instructions
- Compiled the open map stack
I have initialized a new OpenMapStack project for the Tallinn building analysis. This includes a pinned Overture release (2024-03-12-alpha.0) and uses the local L-EST97 (EPSG:3301) projection for all metric calculations.
Tallinn Urban Green Space Analysis Project
| Phase | Tool | Format | CRS |
|---|---|---|---|
| Ingest | DuckDB (httpfs) | GeoParquet | EPSG:4326 |
| Analysis | DuckDB Spatial | GeoParquet | EPSG:3301 |
| Storage | Local Drive | GeoPackage | EPSG:3301 |
| Delivery | PMTiles | MVT | EPSG:3857 |
# project.yaml
project:
name: tallinn-green-build
version: 1.0.0
crs: "EPSG:3301"
inputs:
- name: overture_buildings
source: "s3://overturemaps-us-west-2/release/2024-03-12-alpha.0/theme=buildings/"
type: geoparquet
- name: tallinn_greenery
source: "data/raw/tallinn_parks.gpkg"
type: geopackage
pipeline:
- name: spatial_join
engine: duckdb
script: "scripts/join_greenery.sql"
outputs:
- name: building_density_map
format: pmtiles
path: "data/derived/tallinn_density.pmtiles"
Next steps
- Run
openmapstack validateto check theproject.yamlschema and local source paths. - Execute
openmapstack runto materialize the joined GeoParquet and generate the PMTiles archive. - Open
project.qgzusing free QGIS desktop app to inspect the styled layers and verify the spatial predicates.
Connects securely to your tools. The creator never sees your data.
About this skill
Geospatial engineering often fails due to fragile pipelines, silent CRS mismatches, and unscalable local processing. This skill provides a production-grade framework for building reproducible GIS workflows using an open-source stack.
What it does
- Architects geospatial stacks by selecting authoritative data sources, compute engines, and storage formats based on project scale.
- Builds reproducible pipelines that generate deterministic project artifacts, including QGIS projects and validated data outputs.
- Executes spatial analytics using DuckDB Spatial, PostGIS, and GeoPandas, prioritizing database-level operations over Python loops.
- Optimizes data delivery for web maps using PMTiles, COGs, and STAC discovery for cloud-native access.
- Automates QGIS workflows including project styling, layer management, and PyQGIS scripting for desktop exploration.
How it works
- Discovery and Sourcing involves searching STAC catalogs or Overture datasets to pin authoritative, immutable source data.
- Compute and Analysis defines the transformation logic using spatial SQL or vectorized processing on the chosen engine.
- Project Compilation generates a rerunnable
project.yamlfollowing theopenmapstack-project/v1schema. - Validation and Verification runs automated checks on geometry validity, CRS consistency, and pipeline integrity before delivery.
Frameworks & tools
Built for the modern GIS stack: DuckDB Spatial, PostGIS, GDAL/OGR, MapLibre, PMTiles, Cloud Optimized Geotiffs (COG), GeoParquet, STAC, and QGIS.
Why this beats prompting it yourself
Generic AI often hallucinations coordinates or suggests deprecated formats like Shapefiles. This skill enforces strict geospatial hygiene, such as mandatory CRS verification, license preservation, and cloud-native storage patterns that prevent pipeline breakage at scale.
Use cases
- Generate a rerunnable pipeline to analyze urban building density using Overture data.
- Build a cloud-native web map backend using PMTiles and Martin tile servers.
- Convert legacy GIS scripts into a validated, containerized ETL process.
- Automate the creation of styled QGIS projects with correct projection settings.
Known limitations
Does not support casual place lookups or ordinary travel directions. Requires specific geospatial libraries like GDAL or DuckDB to be available in the execution environment for validation.
Overkill for casual place lookups or non-spatial coding. Requires environment with GDAL/PROJ/DuckDB for validation. Avoids non-reproducible hand-edited QGIS files.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
Allowed Hosts