The Agent Skills Directory

[SAFE]: The skill is composed exclusively of documentation and instructional content. It does not contain any executable scripts, binary files, or automated commands that could be leveraged for malicious purposes.- [SAFE]: The skill implements a 'read-only by default' principle, instructing the agent to perform audits without mutating source code unless specifically requested by the user.- [SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were detected. All external references, such as the mention of 'oklch.fyi', are directed toward well-known, safe design utilities for color calculation.- [SAFE]: The skill does not define any external package dependencies or remote code execution patterns, relying instead on the agent's internal reasoning and the provided design guidelines.

better-interface