The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local utility scripts using uv run for state management and configuration resolution (e.g., {project-root}/_bmad/scripts/memlog.py and {project-root}/_bmad/scripts/resolve_customization.py). These scripts are located within the vendor's expected directory structure.
[COMMAND_EXECUTION]: Platform-specific shell commands (open, xdg-open, start) are used to open generated HTML mockups and validation reports in the user's default web browser for interactive review.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as PRDs and user-supplied design files, creating a potential surface for indirect prompt injection.
Ingestion points: The {planning_artifacts}/ directory, the imports/ folder, and direct user-provided content.
Boundary markers: None explicitly defined in the prompt instructions to separate untrusted data.
Capability inventory: The skill has the ability to write to the file system, execute local scripts, and interact with the system browser.
Sanitization: No specific sanitization or filtering logic is documented for the ingested content.

bmad-ux