The Agent Skills Directory

[SAFE]: The skill is designed for read-only data analysis. Its GraphQL operations are restricted to querying order and refund information without any mutation capabilities.
[DATA_EXFILTRATION]: No unauthorized network operations or exfiltration patterns were detected. The skill processes data locally and outputs results to a standard CSV file.
[COMMAND_EXECUTION]: The skill does not execute arbitrary shell commands. It relies on the structured shopify-admin and shopify-admin-execution toolkits for API interactions.
[PROMPT_INJECTION]: No attempts to override system behavior or bypass safety guidelines were found. The instructions are focused on data aggregation and formatting.

shopify-admin-refund-rate-analysis