[filsteal]

So there are two ways you could do this.

One way is the empirical way. Use tournament/cash game results and show that certain players outperform the average at a statistically significant level.

The other way is the theoretical way. Take a simplified version of poker, do a bunch of game theory calculations, and demonstrate that certain strategies win more money than others. Then argue that if simpler poker variations are skill games, then more complex (i.e., "real") versions must also be skill games. (FWIW, this has already been done, most notably by Chen and Ankenmann in Mathematics of Poker.)