Anthropic hands Agent Skills standard to Linux Foundation group, with security guidance on the roadmap

Anthropic has donated Agent Skills, an open standard that gives AI agents specialised knowledge and workflows, to the Agentic AI Foundation (AAIF), which sits under the Linux Foundation. A skill is a folder containing a SKILL.md file that teaches an agent a specific task, along with any scripts or reference material it needs. Anthropic says more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot and VS Code, have adopted the standard since it was published in December 2025.

Uptake has been rapid. Anthropic reports that 1 million skills have been published and nearly 280 million installed. Because a skill can include scripts as well as instructions, this is a growing body of third-party content that agents may draw on. Anthropic is donating the name, logo, GitHub organisation and the agentskills.io domain. Engineers from Anthropic, Google, OpenAI and other companies will maintain the standard as individuals.

The proposed starting roadmap covers versioned releases, a formal proposal process, and security guidance for people who write and install skills. The source does not detail what that guidance will say. For businesses already using AI agents, the move signals that skills are becoming a common, shared way to extend agent behaviour, and that security practices around them are still being developed.