News for hackers. Stuff that matters.
Re:Agent Skills by storus on Tuesday February 03, 2026 @12:35PM (#46874141)
Yeah but this seems like a bolt-on and not something they train their model to understand at the token level like how they do tool calls. Maybe Anthropic has a token-level skills support (e.g. <SKILL_START>skill prompt<SKILL_END>).

There are no comments on this comment yet.