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 collection provides tools for automation builders to optimize how AI agents handle complex tasks. It focuses on identifying recurring friction signals during coding sessions and establishing governance for when to escalate tasks to more capable models based on reasoning depth.
By converting observed patterns into enforceable rules, the system helps developers move from manual session retrospectives to a structured learning pipeline that reduces repetitive mistakes.
WHO IT'S FOR
AI agent / automation builders
creating secure Claude Code hooks for validation
Platform / DevEx teams
optimizing AI coding workflows via friction detection
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.