The Agent Skills Directory

[SAFE]: The skill provides instructions and rules for performing UX audits on React and Next.js codebases. It does not exhibit any malicious behaviors such as prompt injection, data exfiltration, or obfuscation.
[COMMAND_EXECUTION]: The skill uses standard command-line utilities like ripgrep (rg) and fd to search for specific code patterns within the project's filesystem. These operations are read-only and limited to the scope of the code being audited.
[EXTERNAL_DOWNLOADS]: All external URLs referenced in the rule definitions point to official documentation from trusted organizations (e.g., react.dev, nextjs.org, w3.org, mozilla.org) or reputable UI library sites (e.g., radix-ui.com). These references are used solely for remediation guidance and do not involve downloading or executing untrusted code.
[NO_CODE]: The skill consists of configuration and instructional markdown files. It does not ship with any executable binaries or scripts, relying entirely on the agent's built-in capabilities and standard system tools.

ux-audit