The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were identified in the instructions. The skill uses natural language to define a specific interaction style for design reviews.
[NO_CODE]: The skill consists entirely of a markdown file with behavioral instructions and does not include any scripts, binary files, or external software dependencies.
[COMMAND_EXECUTION]: The instructions suggest that the agent should explore the codebase to answer questions if possible. This utilizes the agent's built-in file navigation capabilities for project analysis and does not involve malicious or unauthorized command execution.

grilling