Dual Axis Skill Reviewer

This is a gate-keeping tool for skill quality. It runs deterministic checks on structure, scripts, and tests, then merges those scores with an LLM-based deep review to produce a weighted final score. You'd use it when you want reproducible numbers before merging new skills, especially if you're enforcing a threshold like 90+. The two-axis approach is smart because you get hard pass/fail criteria plus qualitative code review in one number. It works cross-project via a project-root flag and spits out JSON plus markdown reports with concrete improvement items when scores fall short. The workflow is a bit manual since you run the auto axis, feed a generated prompt to an LLM, then merge the results, but that's the tradeoff for keeping the LLM step flexible.