The Agent Skills Directory

[SAFE]: The skill is a documentation-only framework that reads and writes Markdown and YAML files within the project's directory. It does not perform network requests, execute shell commands, or download external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context to generate decision criteria. While this represents an ingestion surface, the risk is negligible as the skill enforces a human-in-the-loop workflow where the user must review and refine all AI-generated content before final record generation.

adr-methodology