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.
Architect-loop provides a framework for technical leads to design high-quality system foundations using AI. It organizes the transition from initial research to formal specifications through a series of specialized design and review cycles.
The system employs an orchestrator pattern to manage architectural research and codebase design, incorporating adversarial reviews to stress-test technical decisions before implementation begins.
WHO IT'S FOR
Technical leads / architects
designing high-quality codebase architectures with AI
AI agent / automation builders
implementing optimized goal-oriented AI loops
Backend / infrastructure engineers
executing rigorous TDD and integration cycles
QA / test automation engineers
hardening specifications through adversarial testing
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.