The Agent Skills Directory

[SAFE]: The skill provides comprehensive guidelines for analytics engineering and dbt project management. All instructions and patterns align with industry best practices for data modeling and transformation.
[COMMAND_EXECUTION]: The provided Python scripts (impact_analyzer.py, schema_diff.py, doc_generator.py, and quality_scorer.py) are utility tools designed to process dbt manifest and catalog JSON artifacts. Analysis shows these scripts perform only standard local file I/O and data processing without network operations, dynamic code execution, or unauthorized file access.
[EXTERNAL_DOWNLOADS]: The CI/CD workflow example in REFERENCE.md references the installation of dbt-snowflake, which is a standard, well-known adapter for dbt and Snowflake integration.
[INDIRECT_PROMPT_INJECTION]: The skill describes an attack surface where it processes data from dbt artifacts (manifest.json, catalog.json). However, the scripts act as static analyzers and do not feed untrusted data back into agent prompts in an exploitable way. Capability inventory is restricted to local file reads and standard output.

analytics-engineer