Anthropic said on October 22 that it is donating Agent Skills, the open standard it published in December 2025, to the Agentic AI Foundation (AAIF) under the Linux Foundation. A skill is a folder containing a SKILL.md file that teaches an agent a task or domain, plus any scripts or reference material it needs; Anthropic says it built the format while working on Claude Code, which handled general knowledge work but lacked the procedural knowledge real business tasks require. The company reports that more than 70 agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot and VS Code, and that about 1 million skills have been published with nearly 280 million installs. The donation covers the Agent Skills name and logo, the GitHub organization and the agentskills.io domain. AAIF, which Anthropic co-founded with Block and OpenAI and to which it previously donated the Model Context Protocol, becomes the neutral home for the standard. Engineers from Anthropic, Google, OpenAI and other companies will maintain it as individuals, with David Soria Parra and Mahesh Murag as lead maintainers. The proposed roadmap covers versioned releases, a formal proposal process and security guidance for people who write and install skills.
Our takeThe interesting part is not the paperwork but what a portable skill format makes testable: a SKILL.md folder is a procedural artifact you can version, diff and pin per task, unlike prompt text buried inside an application. Versioned releases and security guidance matter because a skill can carry executable scripts that run with the agent's own privileges, so the proposal process will have to settle whether a skill can declare the permissions it needs before it is installed. Worth watching is whether other runtimes adopt identical semantics, not just the same file layout.