The Agent Skills Directory

[SAFE]: The content is entirely instructional, describing a software development process including implementation, testing, and integration gates. It does not contain any executable scripts, shell commands, or network operations.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill references other internal documentation and follows a logical workflow for code review and verification.
[SAFE]: The skill explicitly restricts the agent's authority, stating it adds no power to commit, push, publish, merge, or deploy code, which aligns with security best practices for automated agents.

he-build