By Roman Aglaganov
Anthropic said on 22 October that it is donating Agent Skills, the open standard for giving AI agents specialised knowledge and workflows, to the Agentic AI Foundation (AAIF), part of the Linux Foundation. The foundation already looks after the Model Context Protocol (MCP), which Anthropic also donated.
What a skill is
A skill is a folder containing a SKILL.md file that teaches an agent a particular task or field, plus any scripts or reference material it needs: how to fill in a company’s expense form, say, or how to build a spreadsheet in a house style. The agent loads it only when it is relevant. Anthropic developed skills for Claude Code, launched them in October 2025 and published them as an open standard that December.
Since then, Anthropic says, more than 70 agent platforms have adopted them, including ChatGPT, Cursor, GitHub Copilot and VS Code, and 1 million skills have been published and nearly 280 million installed.
What changes
Anthropic is handing over the Agent Skills name and logo, the GitHub organisation and the agentskills.io domain. Engineers from Anthropic, Google, OpenAI and other companies will maintain the standard as individuals, led by David Soria Parra and Mahesh Murag. Anyone can use it or contribute without joining the foundation. The proposed roadmap starts with versioned releases, a formal process for proposing changes, and security guidance for people who write and install skills.
Why it matters
Standards spread faster when no single company owns them, and a neutral home makes it easier for rivals to keep building on this one. The security guidance is overdue: a skill can include scripts that an agent runs on your machine, so installing one from a stranger carries the same risk as installing any software. A shared rulebook for checking them would help everyone who uses agents.
Disclosure: AI Pulse is written with AI tools, including Claude, which is made by Anthropic.
