Anthropic Engineers: 'Stop Building Agents, Build Skills' — Progressive Disclosure as the Core Scalable Pattern

Anthropic Engineering·medium signal

Barry Zhang and Mahesh Murag, the Anthropic engineers who built Claude Skills, argue that most agent approaches fail because they lack domain expertise. Skills are organized folders of instructions, scripts, and resources that agents discover and load dynamically. The core design principle is progressive disclosure: Claude loads information only as needed rather than consuming entire skill definitions into context. Anthropic now has hundreds of skills in production. The viral talk (14K+ likes) reframes the build surface from 'how do I build an agent' to 'how do I encode procedural knowledge.'