The Agent Skills Directory

[SAFE]: The skill serves as a development guide for internal tooling. It includes security-conscious code samples such as a requireAdmin() wrapper for API routes and rate-limiting logic using createRateLimiter.
[INDIRECT_PROMPT_INJECTION]: The skill describes patterns for fetching and displaying data from internal API endpoints, which represents a standard data ingestion surface.
Ingestion points: React components in src/app/admin/page.tsx fetch data from /api/admin/metrics and /api/admin/stats.
Boundary markers: None explicitly defined in the data transport layer beyond standard JSON structure.
Capability inventory: The skill uses Read, Write, Edit, and Bash tools for dashboard development.
Sanitization: The skill explicitly mandates a "HIPAA-Safe Error Display" pattern in SKILL.md to prevent the leakage of Personally Identifiable Information (PII) or Protected Health Information (PHI).

admin-dashboard