Anthropic researchers say the industry should stop building tons of AI agents - the real breakthrough is something simpler

""The agent underneath is actually more universal than we thought." Instead of building new agents for every use case, companies should rely on a single general agent powered by a library of skills, Zhang said. Skills are "organized collections of files that package composable procedural knowledge for agents," Zhang said. They are simply folders that contain whatever an agent needs to complete a task consistently and efficiently."

""Despite their intelligence, Zhang said today's agents "lack expertise" and often miss important context in real-world use cases. Skills help fill in those gaps by giving agents domain knowledge and reusable workflows. Murag said Anthropic has already seen skills built by people in accounting, legal, recruiting, and other non-technical roles. In the five weeks since launch, users have created thousands of these skills, and large companies are starting to treat them like internal playbooks for AI, he added.""

A single general agent equipped with a library of reusable 'skills' can provide domain expertise and efficient workflows across use cases. Skills are organized collections of files that package composable procedural knowledge and contain whatever an agent needs to complete tasks consistently. Current agents often lack expertise and miss important real-world context; skills supply domain knowledge and reusable workflows to fill those gaps. Non-technical employees across accounting, legal, and recruiting have created thousands of skills within weeks of launch. Large companies and Fortune 100 firms use skills as internal playbooks to teach agents organizational best practices and standardize AI processes.

Read at Business Insider