The Agent Skills Directory

[SAFE]: The skill provides structured instructions for managing implementation, testing, and code review processes. Its primary goal is to improve efficiency and focus on verifiable results.
[SAFE]: The guidance on security findings encourages agents to focus on reachable attack paths and documented assets, while explicitly instructing that actual defects should never be hidden from the user.
[SAFE]: The 'Reviewer Dispatch' mechanism is a workflow template for multi-agent interaction, designed to maintain consistent evaluation criteria across different agent instances.
[SAFE]: No network operations, sensitive file access, credential usage, or remote code execution patterns were detected. The skill is entirely instructional and does not include scripts or binary assets.

agent-guardrails