Agent Skills: universal-learning-signature

Framework for measuring learning dynamics in multi-agent systems and communication networks. Provides D (dimensionality), f (feedback fraction), and H₁ (topological cycles) measurements with confidence scoring. Validates across 4 domains (Topobench synthetic, GitHub networks, IES empirical, DuckDB real). Use this skill when measuring learning system characteristics, verifying convergence in multi-agent systems, comparing learning mechanisms across domains, or trading measurement services in agent marketplaces.