Anthropic hands the Agent Skills standard to a Linux Foundation project

Anthropic is donating Agent Skills to the Agentic AI Foundation, a Linux Foundation project it co-founded last year with Block and OpenAI. A skill is deliberately simple: a folder with a SKILL.md file plus any scripts or reference material the agent needs to follow a specific procedure. Anthropic built the idea while working on Claude Code, which handled general knowledge work well but often missed the step-by-step procedural knowledge that real business tasks require. The donation covers the name and logo, the GitHub organization, and the agentskills.io domain, so the format no longer sits with one company.

The adoption numbers are the reason this matters more than a typical standards hand-off. Anthropic says more than 70 agent platforms have integrated Agent Skills, including ChatGPT, Cursor, GitHub Copilot, and VS Code. Since the standard was published in December 2025, about 1 million skills have been published and nearly 280 million have been installed. Engineers from Anthropic, Google, OpenAI, and other companies will now maintain it as individuals, with David Soria Parra and Mahesh Murag as lead maintainers. The same foundation already hosts the Model Context Protocol, which Anthropic also donated, so there is a precedent for how this kind of handover plays out.

The proposed roadmap adds versioned releases, a formal proposal process, and security guidance for people who write and install skills, which is the part worth watching given that installed skills run scripts on your behalf.

Why it matters

If you build on agents, Agent Skills is now something you can adopt without betting on a single vendor keeping it open, and the same SKILL.md folder should work across ChatGPT, Cursor, Copilot, and Claude. The security guidance on the roadmap is the thing to track, because a skill can carry scripts, and 280 million installs is a large surface to get wrong.