The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified during the analysis of the skill's instructions and reference files.
[COMMAND_EXECUTION]: The skill uses standard file-reading tools (Read, Grep, Glob) to inspect source code. These tools are used according to their intended purpose for code auditing and do not perform unauthorized actions.
[DATA_EXFILTRATION]: No network-capable tools or patterns were detected. All analysis is performed within the local execution environment, and no sensitive file paths are accessed.
[PROMPT_INJECTION]: The instructions contain standard workflow directives and task planning notes to manage agent behavior. No attempts to bypass safety filters or extract system prompts were found.
[EXTERNAL_DOWNLOADS]: The skill references documentation from well-known and trusted sources including the W3C, MDN Web Docs, and web.dev. No executable code or scripts are downloaded or executed from these references.

web-design-guidelines