The Agent Skills Directory

[SAFE]: The skill documentation describes legitimate usage of the GeoPandas library for geospatial analysis. All code examples use standard, public APIs for data manipulation and visualization without any suspicious or unauthorized behaviors.
[EXTERNAL_DOWNLOADS]: The skill references standard, well-known Python packages including geopandas, matplotlib, folium, mapclassify, contextily, pyarrow, psycopg2, and geoalchemy2. These are official libraries commonly used in the geospatial ecosystem and are intended to be installed from established package registries.
[CREDENTIALS_UNSAFE]: Example database connection strings for PostGIS usage employ generic placeholders such as user:pass@host/db, which is consistent with safe documentation practices for demonstrating API usage.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of untrusted geospatial data from external files and databases.
Ingestion points: Data is loaded via gpd.read_file, gpd.read_parquet, and gpd.read_postgis as shown in SKILL.md.
Boundary markers: None explicitly mentioned in the code samples.
Capability inventory: The skill allows writing data back to the file system (to_file, to_parquet) and databases (to_postgis).
Sanitization: The skill relies on standard library-level parsing (Fiona, GDAL, SQLAlchemy) for data validation. This capability is inherent to the primary function of geospatial analysis tools and does not introduce unusual risks.

geopandas-geospatial