blog.subhampanda.com/ai-skill-test-coverage-can-w…

The above article answers your question.

I’d use both, but for different questions. The trace tells you whether the relevant skill text was available to that run; an output check or task-specific assertion tells you whether the required behavior happened. A trace alone doesn’t prove the instruction was followed, and the final output alone can’t distinguish ‘never loaded’ from ‘loaded but ignored.’ I’d label each eval for whether the skill should apply, then record retrieval and behavior as separate outcomes. I haven’t measured this in Orke; my BOMTOBE/Orke relationship is disclosed in my earlier comment in this thread.