The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (resolve_customization.py, resolve_config.py) using uv run. These scripts are located within the project's _bmad/scripts/ directory and are used to manage workflow customization and project configuration.\n- [EXTERNAL_DOWNLOADS]: The skill initiates the installation of the bmad skill from the bmad-code-org/BMAD-METHOD repository on GitHub via npx skills add. This is a vendor-owned resource required for the skill's setup process.\n- [INDIRECT_PROMPT_INJECTION]: The skill assesses change impacts by ingesting various project documents, such as PRDs, architecture guides, and UX designs.\n
Ingestion points: Document Discovery process in SKILL.md loading files from the {planning_artifacts}/ directory.\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potential malicious content within these documents.\n
Capability inventory: The skill can execute shell commands via uv run and write new proposal documents to the file system.\n
Sanitization: No sanitization or validation of the ingested document content is performed before processing.\n- [DYNAMIC_EXECUTION]: Upon completion (Step 6), the skill resolves a value from the workflow.on_complete configuration key and instructs the agent to follow it as the final terminal instruction. This allows for dynamic extension of the skill's behavior based on local configuration files.

bmad-correct-course