The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during activation and completion. This script is a tool provided by the vendor (bmad-code-org) within the project's directory structure.\n- [COMMAND_EXECUTION]: The workflow is designed to execute sequences of shell commands defined in the activation_steps_prepend, activation_steps_append, and on_complete fields of the project's TOML configuration files. This functionality allows for the dynamic execution of commands based on content within the project environment.\n- [PROMPT_INJECTION]: The skill ingests data from external project documentation (GDD, feature specs) and uses it to generate test scenarios, presenting an indirect prompt injection surface.\n
Ingestion points: Reads content from GDD, game-design.md, and project-context.md files located in the project directory.\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing external documentation.\n
Capability inventory: The skill possesses capabilities to execute Python scripts and shell commands as described in the command execution findings.\n
Sanitization: No validation or sanitization of the documentation content is performed before it is processed by the agent.

gds-test-design