The Agent Skills Directory

[SAFE]: The skill follows secure operational practices by defining clear invariants that prohibit the agent from performing high-risk tasks like writing production code or executing git commands. It utilizes a human-in-the-loop model where all generated content must be reviewed and validated by the user. While the skill ingests external data from repository files and documentation, the risk of indirect prompt injection is mitigated by the structured clarification process and the requirement for user approval before completing the context brief.

clarify