The Agent Skills Directory

[SAFE]: The skill content is focused on Salesforce development best practices. It explicitly encourages the use of security-first patterns such as WITH SECURITY_ENFORCED, WITH USER_MODE, and stripInaccessible to prevent unauthorized data access.
[COMMAND_EXECUTION]: The skill includes a Python validation script (scripts/post-tool-validate.py) designed to run as an advisory hook. Analysis shows this script performs safe operations: it reads local .soql files, applies regular expressions to identify common errors (like missing WHERE clauses or hardcoded IDs), and outputs results in JSON format. It does not perform network operations or execute arbitrary system commands.
[EXTERNAL_DOWNLOADS]: No external code downloads or remote script executions were identified. All dependencies referenced (such as the LiveQueryPlanAnalyzer) appear to be local shared modules within the expected repository structure.
[DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The included script only processes query metadata for validation purposes and does not transmit data to external domains.

querying-soql