SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces

ArXi:2605.15215v1 Announce Type: new Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm