The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts using the uv run command for configuration and customization tasks. These scripts are located within the project's own directory at {project-root}/_bmad/scripts/resolve_customization.py, which is a standard location for vendor-provided tooling in this ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from external project documents to extract requirements, which creates a surface for potential indirect prompt injection if the source files contain malicious instructions. 1. Ingestion points: Files matching patterns such as *gdd*.md, *architecture*.md, and *ux*.md in the project's planning artifacts directory. 2. Boundary markers: None; the skill reads the full content of these documents as directed. 3. Capability inventory: Ability to execute local scripts via uv run and write to local files in the project workspace. 4. Sanitization: No specific sanitization or filtering of extracted content is performed.

gds-create-epics-and-stories