Your skills need an evaluation mechanism
Expo Blog
Expo added an evaluation harness to measure whether coding agents actually trigger and use its Expo skills during app-development tasks.
Why it matters
Expo built a CI evaluation harness that measures whether coding agents discover relevant skills, follow their guidance, and produce working apps. They found that adding an overview skill raised sessions loading at least one downstream Expo skill from 9% to 55%, and they stress that names/descriptions must survive truncation.