It does for me. You need to ensure that they are injected into context. Your models might be broken if they ignore it. As good as ignoring a prompt.
That's what the study says.
I recently did a much smaller scale test. Some coworker was pestering me about some brilliant skill file so i backed up Claude's state and told it to make a plan for some refactoring task with and without those skills installed.
The results were identical. I didn't measure token use though.