The Agent Skills Directory

[SAFE]: The skill provides a comprehensive set of instructional markdown files and reference guides for code review. It does not include any executable scripts, tool configurations, or automated network requests.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided source code, which creates a theoretical surface for indirect prompt injection if the code contains adversarial instructions. However, the risk is negligible as the skill lacks high-privilege tools or autonomous action capabilities. * Ingestion points: User-supplied Swift and SwiftUI source code files. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined. * Capability inventory: The skill provides textual analysis only and lacks file-system, network, or code execution capabilities. * Sanitization: No sanitization logic for ingested code is present.

swiftui-pro