The Agent Skills Directory

[SAFE]: The skill's primary function is to provide instructional guidance and architectural oversight for software development tasks. It uses established, reputable industry standards (e.g., Clean Code, Pragmatic Programmer, OWASP ASVS) as its philosophical and technical anchors.
[SAFE]: The skill implements a strict multi-phase workflow (Spec-First Development) with mandatory 'Quality Gates' for security and architecture. It specifically uses the 'evaluator' agent (Opus) to audit code artifacts produced by the 'worker' agent (Sonnet), ensuring a separation of concerns between production and validation.
[SAFE]: Security is a non-negotiable foundation. The skill includes comprehensive standards for application security (OWASP ASVS v5.0.0) and character encoding security (Tokumaru-bon), providing deep technical grounding for preventing injection, credential exposure, and logic flaws.
[SAFE]: All external references and documentation sources mentioned (such as asvs.dev, owasp.org, and official developer blogs) are reputable and well-known technology or academic resources. No suspicious URLs or non-standard delivery domains were found.
[SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was detected. The instructions prioritize transparency and behavior-preserving transformations (refactoring).

code-team