Skip to content
Get packs

GeoPandas Spatial Data Skill

Guides an agent through safe GeoPandas vector-data work with local audit scripts for CRS, geometry, joins and exports.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
14 files

What it does

This skill gives an AI agent detailed guidance for working with GeoPandas, a Python library for geographic vector data such as points, lines and polygons in table form. Once installed, the agent follows explicit correctness checks (coordinate reference system, geometry validity, join cardinality, output contracts) and can run bundled local scripts that inspect files, plan reprojections and exports, and flag privacy-sensitive location fields without transforming data themselves. Those scripts are described as planning and reporting tools; the actual analysis and writing of output remains a separate step.

Great for

  • Analysts and developers writing Python code that uses GeoPandas on local shapefiles, GeoPackages or GeoParquet files
  • Teams that need an audit trail of CRS, source hashes and join counts before sharing geospatial results
  • People handling location data who want a checklist to generalize or redact coordinates before publishing maps

Skip it if

  • Raster imagery or gridded data, which GeoPandas does not handle (reason: the skill covers planar vector data only)
  • Quick web-map styling or hosted GIS services where no Python analysis is involved (reason: the skill targets GeoPandas code, not other GIS tools)
  • Analyses on untrusted files without a sandbox (reason: GDAL and PROJ are native-code components that parse input and the skill itself warns to isolate untrusted data)

Try asking

  • “Check the CRS and geometry validity of my local parcels.gpkg before I compute areas.”
  • “Plan a reprojection from EPSG:4326 to a suitable projected CRS for distance measurements, without transforming the data yet.”
  • “Audit a spatial join between my points and census polygons for unmatched and duplicated rows.”
  • “Review whether my exported point layer contains coordinates that should be generalized before sharing.”
Step-by-step guide: how to use GeoPandas Spatial Data SkillInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 14 original files, the MIT licence and an attribution note.

    geopandas.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip geopandas.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip geopandas.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Ask the agent to run the inventory and CRS plan first, so it confirms the coordinate system before any measurement.
  • Keep the pinned environment in a project lock file and do not mix binary geospatial packages from different channels.
  • Treat scripts' output as a plan: write results to a new file path and reopen it to confirm counts and types.

What's inside

  • references/crs-management.md
  • references/data-io.md
  • references/data-structures.md
  • references/geometric-operations.md
  • references/spatial-analysis.md
  • references/visualization.md
  • scripts/_common.py
  • scripts/crs_reprojection_plan.py
  • scripts/export_plan.py
  • scripts/geometry_validity_report.py
  • scripts/sensitive_coordinates_checklist.py
  • scripts/spatial_join_audit.py
  • scripts/vector_inventory.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.