The Agent Skills Directory

[SAFE]: The skill contains strictly behavioral instructions and markdown templates for code review. There are no executable scripts, shell commands, or network operations included.
[SAFE]: No prompt injection or behavior override patterns were detected; the instructions serve to focus the agent's role on technical criticism and logic validation.
[SAFE]: Code examples provided within the skill (such as JWT verification fixes) are standard technical illustrations and do not contain hardcoded credentials or sensitive data.
[SAFE]: Resource links point to other local skill files within the same environment using relative paths, which is expected for modular skill sets.

critical-partner