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.
CCFA-Skills provides a structured system for managing the lifecycle of AI experiments and agent interactions. It establishes shared governance through routing, trigger registries, and artifact contracts to ensure consistency across complex task modes.
The toolkit helps researchers and developers define precise experiment semantics, from selecting baselines and metrics to specifying the exact schema of result tables and robustness tests.
WHO IT'S FOR
AI research scientists
designing experiment evidence and benchmark planning
Academic writers
refining publication-facing AI prose and artifacts
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.