The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the great_expectations package via pip. This is a well-known and widely used library for data validation. It also includes links to official documentation for Great Expectations, dbt, and Soda Core.
[INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and validating data from external databases and warehouses, creating a surface for potential injection from untrusted data sources.
Ingestion points: Data is loaded via gx.get_context() and context.run_checkpoint from configured datasources (e.g., 'warehouse') as seen in SKILL.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded content within the processed data are provided in the validation logic.
Capability inventory: The skill uses Python and SQL to perform validations, generates markdown reports, and can send notifications via Slack webhooks using environment variables for configuration as defined in SKILL.md.
Sanitization: No evidence of data sanitization or escaping is present in the logic that processes observed values for reporting.

data-quality-frameworks