The Agent Skills Directory

[SAFE]: The skill consists of markdown-based instructions for design simplification, information architecture refinement, and code cleanup. It does not contain executable code segments or scripts.
[PROMPT_INJECTION]: The instructions use emphasized terms such as 'MANDATORY', 'CRITICAL', and 'IMPORTANT' to enforce design principles (e.g., following established protocols and justifying every UI element). These are legitimate instructional markers and do not attempt to bypass agent safety filters or override core system behavior.
[COMMAND_EXECUTION]: While the skill instructs the agent to perform 'Code Simplification' (e.g., removing unused code or flattening component trees), it does not provide specific shell commands or scripts. It relies on the agent's existing capabilities to interact with the codebase.
[EXTERNAL_DOWNLOADS]: No network operations, external URL fetches, or remote script inclusions were detected. All references are internal to the expected project environment (e.g., loading related design skills).
[DATA_EXFILTRATION]: There are no patterns indicating the collection or transmission of sensitive data to external domains. The skill focuses entirely on design and code refinement within the user's project context.

distill