The Agent Skills Directory

[SAFE]: The skill 'normalize' is designed to help an AI agent align UI components with a specific design system. It contains instructions for auditing typography, color, layout, and hierarchy within a local repository.- [COMMAND_EXECUTION]: The instructions suggest using the grep command to locate design system documentation within the local workspace. This is a standard and benign use of search tools for context gathering.- [DATA_EXFILTRATION]: No network-enabled tools or commands (e.g., curl, wget) are present in the instructions. The skill operates entirely on local repository files and does not attempt to access sensitive system directories or credentials.- [PROMPT_INJECTION]: The skill uses directive language like 'CRITICAL' and 'MANDATORY' to ensure the agent follows specific design protocols. These are functional instructions for the task and do not attempt to override the AI's core safety guidelines or extract internal system prompts.

normalize