equivariant-architecture-designer

SKILL.md

This skill helps you design neural network architectures that respect identified symmetry groups. Given a validated group specification, it recommends architecture patterns, specific libraries, and implementation strategies.

The payoff: Equivariant architectures have fewer parameters, train faster, generalize better, and are more robust to distribution shift.

Gather the validated group specification. Confirm: which group(s) are involved, whether invariance or equivariance is needed, the data domain (images, point clouds, graphs, etc.), task type (classification, regression, generation), and any computational constraints. If group isn't specified, work with user to identify it first.

Úselo cuando haya validado grupos de simetría y necesite diseñar una arquitectura de red neuronal que respete esas simetrías. Invocar cuando el usuario menciona capas equivariantes, G-CNN, e3nn, redes orientables, creación de simetría en el modelo o necesita recomendaciones de arquitectura para grupos de simetría específicos. Proporciona patrones de arquitectura y orientación de implementación. Fuente: lyndonkl/claude.

Ver original