skills

This collection provides modular, composable agent skills designed to improve software engineering workflows and reduce common AI coding failures. The tools focus on core principles like alignment, shared domain language, and rigorous feedback loops to prevent codebase entropy. These skills are easily installed and adaptable, allowing developers to integrate professional engineering practices directly into their coding agents.

This project provides a collection of modular, composable skills designed to enhance the performance and reliability of AI coding agents by grounding them in established software engineering fundamentals. It addresses common agent failure modes—such as misalignment, excessive verbosity, and poor code quality—by enforcing structured workflows like domain-driven design, test-driven development, and rigorous diagnostic loops. The design philosophy prioritizes developer control and adaptability, favoring small, specialized tools over monolithic processes that can obscure the development lifecycle.