we_are_coded.by CODE · The world, decoded
БГ

Anthropic · Builders

Anthropic donates Agent Skills to the Linux Foundation, next to MCP: engineers from Anthropic, Google and OpenAI will maintain the standard as individuals

On October 22, Anthropic announced it is donating Agent Skills to the Agentic AI Foundation under the Linux Foundation, where MCP already lives. The name, the logo, the GitHub organization and the agentskills.io domain go with it. Per Anthropic, more than 70 agent platforms already use it.

Source
Anthropic
Published
The event
Checked on
Responsible editor
Cvetelin Ivanov
How we work
MethodCorrections

A skill is a folder. Inside is a SKILL.md file that says how to do one task. The folder can carry scripts, too.

Fact

The facts: on October 22, 2026, Anthropic announced it is donating Agent Skills, the open standard that gives AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF) under the Linux Foundation. Anthropic co-founded AAIF with Block and OpenAI last year and donated the Model Context Protocol (MCP) there. The Agent Skills name and logo, the GitHub organization and the agentskills.io domain are donated too. Engineers from Anthropic, Google, OpenAI and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers. Per Anthropic, more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot and VS Code, have integrated it since it was published in December 2025; 1 million skills have been published and installs are near 280 million. Anthropic writes that the standard stays open, community-driven and vendor-neutral, and that you can use it or contribute to it without joining AAIF.

What moves is the question of who decides what goes into the standard. Until now the standard was Anthropic's. From here, on paper, it is “the maintainers”: engineers from three competing labs and from other companies, at one table and as individuals.

The folder is the same. The one who decides what goes into it changes.

The path ahead is for now a proposal from Anthropic, not a decision of the foundation: versioned releases, a formal proposal process and security guidance for people who write and install skills. The last one is the most practical, because a skill can carry scripts, and scripts are someone else's code inside your agent.

The security guidance is not out yet. Until then, you open the folder and read SKILL.md and the scripts before you put it into your agent.

The visual is generated code-art, no third-party images.