The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes uv run to execute a script located at {project-root}/_bmad/scripts/resolve_customization.py. This script is part of the vendor's orchestration framework and is used to resolve workflow customizations from project-local configuration files.- [DYNAMIC_EXECUTION]: The skill executes sequences of activation steps and a terminal on_complete instruction defined in customize.toml or its project-specific overrides. While this allows for flexible workflow behavior, it involves the execution of strings as instructions or commands within the local environment.- [INDIRECT_PROMPT_INJECTION]: The skill parses untrusted data from markdown epic files to extract story metadata for the sprint status report.
Ingestion points: All files matching *epic*.md in the {planning_artifacts} directory are read to extract epic and story information.
Boundary markers: None are specified; the skill relies on standard Markdown header patterns (e.g., ## Epic n:) to structure the data.
Capability inventory: The skill has the capability to write YAML files to the local file system and execute local Python scripts via uv run.
Sanitization: Story titles and IDs are sanitized into kebab-case keys (e.g., 1-1-user-authentication) before being written to the output YAML file, which mitigates simple injection attempts in the generated output.

gds-sprint-planning