The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests groundwater observations and meteorological data from external CSV files.
Ingestion points: Data is read via scripts/run_pastas_workflow.py from files specified in a project configuration.
Boundary markers: The script enforces a two-column CSV structure and rigorous data validation using Pandas.
Capability inventory: Modeling capabilities are focused on numerical analysis and local file I/O for results.
Sanitization: Input data is strictly converted using pandas.to_numeric and pandas.to_datetime with error raising, ensuring only valid scientific data enters the modeling pipeline.
[DYNAMIC_EXECUTION]: The skill provides an example of loading its internal workflow script using importlib.util.spec_from_file_location. This pattern is used for modular tool integration and targets a script distributed with the skill itself.
[EXTERNAL_DOWNLOADS]: The skill references the official GitHub repositories for the Pastas library and USGS datasets. These references provide necessary documentation and provenance information from established scientific sources and well-known services.

hydrogeological-analysis