Anthropic is donating Agent Skills, its open standard for giving AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF), a Linux Foundation project, the company said on Thursday.
The transfer covers the Agent Skills name and logo, the project’s GitHub organization and the agentskills.io domain, according to Anthropic. Developers can keep using the standard or contribute to it without joining the AAIF, the company said.
Anthropic said more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot and VS Code, have integrated Agent Skills since it published the standard in December 2025. The company said 1 million skills have been published so far and nearly 280 million installed.
A skill is a folder containing a SKILL.md file that teaches an agent a specific task or domain, along with any scripts or reference material it needs. Anthropic said it developed skills while working on Claude Code and launched them in October 2025.
The move follows Anthropic’s donation of the Model Context Protocol (MCP) to the AAIF, which Anthropic co-founded with Block and OpenAI in December 2025, The Register reported. Engineers from Anthropic, Google, OpenAI and other companies will maintain Agent Skills as individuals, with David Soria Parra and Mahesh Murag as lead maintainers, Anthropic said. The company has proposed a roadmap covering versioned releases, a formal proposal process and security guidance for people who write and install skills.
The AAIF announced Agent Skills alongside three other new projects at AGNTCon + MCPCon North America in San Jose: Open Responses from OpenAI, OpenEnv from Hugging Face and OpenSandbox from Alibaba. The additions bring the foundation to 10 hosted projects, up from three at launch, the Linux Foundation said. The Register reported that the AAIF has passed 300 members.
Separately, Anthropic said on Thursday that auto mode will roll out next week as the default for new sessions in most Claude apps on Pro, Max and Team plans. Instead of asking users to approve each action, an automated check lets safe actions proceed and blocks risky ones. Enterprise admins will get an email before the change reaches their organizations, the company said.
Sources
- Anthropic: Donating Agent Skills to the Agentic AI Foundation (October 22, 2026)
- Linux Foundation: Agentic AI Foundation Announces Four New Projects: Agent Skills, Open Responses, OpenEnv, and OpenSandbox (October 22, 2026)
- The Register (Claburn): Vendor-affiliated AI agent tech gets adopted by friendly, funded foundation (October 23, 2026)
- Claude: Auto mode is now the default in Claude Code for Pro, Max, and Team plans (updated October 22, 2026)