The Agent Skills Directory

[SAFE]: The skill provides structured design guidelines based on Apple's Human Interface Guidelines. The content is educational and instructional, focusing on UX principles such as modality, feedback, and accessibility.
[SAFE]: The skill demonstrates security awareness by including 'Implementation checks' in every reference file. These checks warn against executing dropped programs, treating external URLs as trusted, or failing to validate data on the server, which are critical security best practices.
[INDIRECT_PROMPT_INJECTION]: The skill instructions define an attack surface by directing the agent to read external project context.
Ingestion points: The skill instructs the agent to read .claude/apple-design-context.md from the project environment.
Boundary markers: None specified; the agent is advised to treat the file as project context.
Capability inventory: The skill is primarily instructional and does not request specific tool execution permissions in its metadata.
Sanitization: No specific filtering or escaping instructions are provided for the context file contents.

hig-patterns