Two Jev calls cut a Claude agent's wrong-skill rate from 16.8% to 7.3%
Hermes compresses 182 skill descriptions to 60 characters, causing confusion, so the author adds two Jev calls before skill selection: rank all skills, reread the top three, and use a 0.30 threshold to decide whether to suggest anything.
TypeSafe just halved how often a Claude agent loads the wrong skill Hermes cuts every skill description to 60 characters, so lookalikes get mixed up. two Jev calls now sit in front of that pick: 182 skills -> rank all -> reread the top 3 -> suggest one or nothing the whole recipe, animated on one page: > watch 182 skills narrow down to one suggestion > see the pick flip once the full text gets read > steal the 0.30 floor that decides when to suggest nothing 16.8% -> 7.3% wrong skill loads for Claude Haiku 4.5 on Nous Research's Hermes roster. a cheap fix for any agent carrying a big skill folder
This post quotes another post: “Jev vs GPT-5.5 and Opus 4.8: 15-run content moderation consistency test”