Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
This repository provides a structured framework for AI-first development, specifically designed for tools like Claude Code and Codex. It establishes a rigorous path from project knowledge and user-spec planning to execution, ensuring that AI-generated code adheres to specific infrastructure conventions.
The methodology introduces evidence-gated reviews and standardized documentation management, helping developers maintain control over AI agents while scaling software engineering tasks.
WHO IT'S FOR
AI agent power users
implementing intent-driven AI development workflows
Technical leads / architects
standardizing AI-assisted coding and review gates
Full-stack developers
accelerating feature delivery via AI-first writing
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.