The Agent Skills Directory

[SAFE]: The skill's instructions are entirely focused on legitimate frontend development tasks such as refactoring code for consistency and adhering to design systems.
[COMMAND_EXECUTION]: The skill suggests using search tools like grep to locate design system documentation within the local repository. This is a standard and safe operation for a development-oriented agent.
[PROMPT_INJECTION]: The skill includes persona-setting instructions (e.g., "You are a brilliant frontend designer") to define the agent's behavior and aesthetic judgment. These are standard formatting instructions and do not attempt to bypass safety filters or override core system instructions.
[DATA_EXFILTRATION]: While the skill involves analyzing local source code and documentation, it does not contain any instructions to transmit this data externally or access sensitive system paths (like credentials or SSH keys).

normalize