The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various shell commands including git diff, git log, and gh pr view. It also uses uv run to execute a script located at {project-root}/_bmad/scripts/resolve_customization.py during activation and wrap-up.
[DYNAMIC_EXECUTION]: The skill is designed to execute sequences of steps and final instructions defined in configuration files (activation_steps_prepend, activation_steps_append, and workflow.on_complete). In step-05-wrapup.md, the agent is explicitly instructed to execute the string returned for on_complete as a terminal instruction. This allows for arbitrary command execution defined in project-level configuration.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from commit messages, PR descriptions, and external specification files to generate review trails and intent summaries. * Ingestion points: Data is fetched via gh pr view, git diff, and by reading .md and .yaml files from the project root. * Boundary markers: The instructions do not define delimiters or specific "ignore" instructions for the ingested content to prevent the agent from following instructions embedded in the data. * Capability inventory: The agent possesses capabilities for shell execution, network access (via the gh tool), and file system interaction. * Sanitization: No validation or sanitization is performed on the ingested strings before they are used in the agent's context.

bmad-walkthrough