Anthropic releases enterprise AI skills as open standard

Anthropic has released Agent Skills as an open standard, making the technology available across different AI platforms. The company first introduced skills in October as a way to teach Claude repeatable workflows. Now the system works beyond Claude, with Microsoft, Cursor, and other platforms adopting it.

Skills are folders containing instructions and scripts that tell AI systems how to perform specific tasks consistently. Instead of writing detailed prompts each time, users can package procedural knowledge into reusable modules. Each skill uses only a few tokens when summarized, with full details loading only when needed.

The company has added organization-wide management tools for Team and Enterprise customers. Administrators can now provision skills centrally, controlling which workflows are available across their organizations. Anthropic has launched a directory featuring skills from partners including Atlassian, Figma, Canva, Stripe, Notion, and Zapier.

According to Mahesh Murag, a product manager at Anthropic, enterprise customers are using skills in production across legal, finance, accounting, and data science. The GitHub repository has received over 20,000 stars, with thousands of community-created skills.

OpenAI has adopted similar architecture in ChatGPT and its Codex CLI tool, using the same file naming conventions and directory organization. Anthropic donated its Model Context Protocol to the Linux Foundation and co-founded the Agentic AI Foundation alongside OpenAI and Block.

Skills are included in all Claude plans at no additional cost. The company recommends installing skills only from trusted sources and thoroughly auditing those from less-trusted origins.

Sources: Claude Blog, VentureBeat

About the author

Related posts:

Stay up-to-date:

Advertisement