The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/run_postgres_test.sh script is a wrapper designed to execute arbitrary shell commands provided by the agent, such as go test or other language-specific test runners.
[DYNAMIC_EXECUTION]: The helper script uses the "$@" pattern to execute its arguments, providing a direct channel for the agent to perform dynamic command execution based on its instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes 'backend business SOPs' which may be sourced from external documentation or files. This creates a surface for indirect instructions to influence the agent.
Ingestion points: Business SOP descriptions and backend service entry point definitions are ingested to establish the test contract.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading the SOP content.
Capability inventory: The skill allows shell command execution, Docker container management, and file system access within the target project repository.
Sanitization: No sanitization or validation steps are defined for the SOP data before it is translated into test logic and executed.
[EXTERNAL_DOWNLOADS]: The skill pulls the official postgres:16-alpine image from Docker Hub, a well-known service, to establish the testing environment.

verify-backend-sop-db