Expose and document VGP variational parameters for fit diagnostics

The VGP Opper-Archambeau variational parameters carry per-point meaning that could be exposed for diagnostics. alpha is the expected score (a representer weight and pseudo-residual showing each point's influence) and lambda is the expected per-point information (the effective precision). Their reading depends on the likelihood: under Poisson lambda is the expected rate, under Bernoulli it peaks at the decision boundary, and under Student-t it drops toward zero for discounted outliers. Adding a helper to extract alpha, lambda, and diag(S) from a fit aligned to the training inputs, with the per-likelihood interpretations documented and checked against the Opper and Archambeau (2009) paper, would be worth doing. A skill file describing how to read these parameters for fit and data diagnosis should be included as well.

No file or test is named; start by locating the VGP Opper-Archambeau fit state and how its training inputs are represented. Check alpha, lambda, and diag(S) against the Opper and Archambeau (2009) paper, then define completion as an aligned extraction helper, per-likelihood documentation, diagnostic checks, and the requested skill file.