Agent Skills standard moves to a neutral foundation, with 70-plus platforms and one million skills published
Synopsis
Anthropic has donated Agent Skills, the open standard it published in December 2025, to the Agentic AI Foundation under the Linux Foundation, transferring the name, logo, GitHub organization and agentskills.io domain. A skill is a folder holding a SKILL.md file that teaches an agent a specific task or domain; the format grew out of Claude Code, which handled general knowledge work but often lacked the procedural knowledge real business tasks need. Since the October 2025 launch, one million skills have been published and installed nearly 280 million times, and more than 70 agent platforms including ChatGPT, Cursor, GitHub Copilot and VS Code have integrated the standard.
Interpretation
Agent skills have moved from an in-house mechanism at one company to an open standard hosted by a neutral foundation, so any agent platform can read skills in the same format. Skills began as a mechanism Anthropic used while developing Claude Code, which handled general knowledge work well but often lacked the procedural knowledge real business tasks need. After the standard was published in December 2025, more than 70 agent platforms including ChatGPT, Cursor, GitHub Copilot and VS Code integrated it, and developers wrote loaders for Codex, Cursor and OpenCode.
A skill is a folder containing a SKILL.md file that teaches an agent a specific task or domain, together with any scripts or reference material it needs. The format keeps procedural knowledge in files outside the agent instead of requiring each platform to build it in. Within weeks of the October 2025 launch, developers published thousands of skills on GitHub; one million skills have now been published and installed nearly 280 million times.
The donation covers the Agent Skills name and logo, the GitHub organization and the agentskills.io domain, and the standard stays open, usable and contributable without joining the foundation. Anthropic had already donated the Model Context Protocol to the same foundation, following the same path. The Agentic AI Foundation was co-founded last year by Anthropic with Block and OpenAI and sits under the Linux Foundation; engineers from Anthropic, Google, OpenAI and other companies maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers.
Perspective
The report covers the standard's transfer and the ecosystem's scale, aimed at platform developers and skill authors who need to give agents task-specific procedural knowledge. After the transfer the foundation provides neutral hosting, engineers maintain the standard as individuals, and it stays open, usable and contributable without joining the foundation.
The proposed roadmap covers versioned releases, a formal proposal process and security guidance for people who write and install skills, and remains a proposal. Where the standard goes next depends on community input and transparent decision-making, and specific specification changes are still to be discussed.