Anthropic Gives Agent Skills Standard to the Agentic AI Foundation

Anthropic is donating the open Agent Skills standard to the Linux Foundation's Agentic AI Foundation so it stays vendor-neutral and community-driven. The standard is already used by more than 70 agent platforms.

anthropic • Oct 22, 2026

Anthropic is handing over Agent Skills to the Agentic AI Foundation (AAIF). Agent Skills is the open standard that gives AI agents specialized knowledge and workflows. Since the standard was published in December 2025, more than 70 agent platforms have adopted it, including ChatGPT, Cursor, GitHub Copilot, and VS Code.

Agent interoperability through simplicity

A skill is a folder with a SKILL.md file. The file teaches an agent a particular task or domain, and the folder can also hold any scripts or reference material the agent needs. Anthropic developed skills while working on Claude Code. Claude Code handled general knowledge work well, but it often lacked the procedural knowledge that real business tasks require. Within weeks of Anthropic's October 2025 launch, developers had published thousands of skills on GitHub. They also wrote loaders for Codex, Cursor, and OpenCode. Anthropic then released Agent Skills as an open standard, with its own GitHub organization and domain, so that any agent could use it. To date, 1 million skills have been published and nearly 280 million have been installed.

Donating Agent Skills to AAIF

Anthropic is committed to keeping Agent Skills open, community-driven, and vendor-neutral. The standard is going to the AAIF, which sits under the Linux Foundation. Anthropic co-founded the AAIF with Block and OpenAI last year, and it also donated the Model Context Protocol (MCP) to the foundation. The AAIF will act as a neutral home for the standard and make sure the community has a say in its direction.

The donation covers the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain. People can keep using the standard or contribute to it without joining the AAIF.

Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals. David Soria Parra and Mahesh Murag will serve as Lead Maintainers.

What comes next

Anthropic has proposed an initial roadmap that includes versioned releases, a formal proposal process, and security guidance for people who write and install skills. As with MCP, the project will keep prioritizing community input and transparent decision-making. People can join the project's Discord to give feedback on proposed specification changes.

Anthropic thanks the developers who built with Agent Skills from the beginning and the teams who added skills to their products. The specification is available at agentskills.io, and the discussion continues on GitHub.