The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (resolve_customization.py and resolve_config.py) found in the {project-root}/_bmad/scripts/ directory using the uv run command. These scripts are part of the framework's configuration management.\n- [DYNAMIC_EXECUTION]: The skill's activation workflow (SKILL.md, Steps 2 and 7) involves executing entries from the activation_steps_prepend and activation_steps_append arrays. This provides a mechanism for running arbitrary tasks defined in external configuration files.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including project-level configuration files and files referenced in persistent_facts. These inputs are merged into the agent's persona and context, creating a surface for indirect prompt injection.\n
Ingestion points: Configuration files (customize.toml, config.toml) and file contents loaded via the file: prefix in persistent_facts (SKILL.md, Step 4).\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this ingested content as untrusted or separate from its core instructions.\n
Capability inventory: The skill has the ability to execute shell commands (uv run, npx) and dispatch requests to other specialized skills.\n
Sanitization: The skill does not appear to perform sanitization or validation of the ingested external content before it is used to define the agent's behavior.\n- [EXTERNAL_DOWNLOADS]: The skill can initiate the installation of a remote knowledge base using npx skills add bmad-code-org/bmad-method-test-architecture-enterprise. This download targets the author's own official GitHub organization.

bmad-tea