The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill defines a set of heuristics for UI design critique and instructs the agent to perform local code modifications to improve visual quality.- [COMMAND_EXECUTION]: The skill uses grep to scan local configuration and source files (e.g., package.json, Tailwind configs, CSS files). These operations are restricted to the local development environment and are standard for code-editing agents.- [DATA_EXFILTRATION]: There are no network operations, external URL requests, or attempts to access sensitive credentials or environment files.- [PROMPT_INJECTION]: The instructions are purely functional and focused on UI remediation. They do not contain techniques to bypass safety filters or override agent behavior.- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It relies on local tools and rules defined within the skill itself.

ai-tells