symmetry-validation-suite

SKILL.md

This skill provides empirical tests to validate symmetry hypotheses. Before committing to an equivariant architecture, you should verify that your claimed symmetries actually hold. This skill gives you concrete testing protocols and metrics.

Why validate? Wrong symmetry assumptions hurt model performance. Too much symmetry over-constrains; missing symmetry wastes capacity.

Gather candidate symmetries from previous discovery work. For each, document: the transformation type, whether invariance or equivariance is expected, and confidence level. Prioritize testing low-confidence hypotheses. If no hypotheses exist, work with user through domain analysis to identify candidate symmetries first.

Use when you need to empirically test whether hypothesized symmetries actually hold in your data or model. Invoke when user mentions testing invariance, validating equivariance, checking if symmetry assumptions are correct, debugging symmetry-related model failures, or needs data-driven validation before committing to equivariant architecture. Provides test protocols and metrics. Source: lyndonkl/claude.

View raw