The Agent Skills Directory

[SAFE]: The skill is purely instructional, focusing on UI architecture, design tokens, and component contracts.
[SAFE]: Tool usage is restricted to Read and Grep for the purpose of auditing local component libraries and token files as described in the methodology.
[SAFE]: Metadata and external repository links (jacob-balslev/skill-graph) correctly reference the author's own infrastructure and present no security risk.
[SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found.

design-system-architecture