The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script at {project-root}/_bmad/scripts/resolve_customization.py to handle configuration merging during the activation phase and upon completion.
[COMMAND_EXECUTION]: The workflow performs execution of steps specified in the activation_steps_prepend and activation_steps_append configuration arrays, allowing for arbitrary command execution within the project environment.
[INDIRECT_PROMPT_INJECTION]: The skill loads information from {project-root}/**/project-context.md files and treats them as foundational context, which could allow instructions in those files to influence agent behavior.
Ingestion points: SKILL.md identifies {project-root}/**/project-context.md as a source for persistent facts in the activation section.
Boundary markers: No specific delimiters or safety instructions are provided to the agent for isolating this content from its primary instructions.
Capability inventory: The skill possesses file-writing capabilities for framework scaffolding and local command execution capabilities via Python scripts.
Sanitization: No sanitization or validation of the ingested context files is performed.

gds-test-framework