The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses uv run to execute local Python scripts (scripts/parse_owl.py, scripts/generate_artifacts.py, and scripts/visualize_ontology.py) which process ontology data and generate deployment artifacts.
[EXTERNAL_DOWNLOADS]: The skill's Python scripts depend on third-party libraries including rdflib, pyyaml, streamlit, and streamlit-agraph, which are expected to be installed from public registries.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external data (OWL files) to generate executable SQL and semantic model configurations.
Ingestion points: scripts/parse_owl.py reads user-provided ontology files in OWL, RDF, or Turtle formats.
Boundary markers: No explicit delimiters or boundary markers are utilized when interpolating data from parsed ontologies into generated SQL templates.
Capability inventory: The skill possesses the capability to execute SQL via snowflake_sql_execute, run local Python scripts via uv, and write files to the local filesystem.
Sanitization: scripts/generate_artifacts.py includes a sql_escape function that performs single-quote escaping on string literals to mitigate SQL injection during artifact generation.
[DYNAMIC_EXECUTION]: The scripts/generate_artifacts.py script dynamically constructs Snowflake SQL DDL and DML statements and YAML configurations at runtime based on the logical structure defined in the provided ontology files.

ontology-semantic-modeler