This is a good idea - I've been manually doing something similar for almost a year now. It's interesting to find when GPT-5.5 will catch issues with Opus-4.8's code, and vice versa. Good thinking to make it a skill.

Thank you for the kind words! It is amusing that the first few second opinions tend to be all over the places, after back and worth with a few models, the area of contentions seem to settle. Having said that, I've also experienced none of the second opinions were addressing the actual issue.