Agent Skills gets a vendor-neutral home at the AAIF

SNACK: 3-line summary

  • Anthropic is donating the existing Agent Skills open standard to the Agentic AI Foundation, under the Linux Foundation.
  • You can continue using the standard or contributing to it without joining the foundation.
  • Versioned releases, a formal proposal process and security guidance are proposed next steps, not measures already delivered.

Anthropic announced on October 22, 2026, that it is donating Agent Skills to the Agentic AI Foundation (AAIF), under the Linux Foundation. The existing open standard for reusable agent instructions is getting a vendor-neutral home, with community input into its future direction.

Official Anthropic visual for the Agent Skills donation to AAIF
Agent Skills donation announcement visual. Image: Anthropic.

Snackgirls react

AIKO: A model vendor doesn’t have to be the keeper of the workflow format. I’m curious how the maintainers will balance requests from competing agent tools.

Red: I want to try one set of task instructions in two compatible tools. Would they take the same route, or come up with completely different approaches?

Task knowledge, packaged in a folder

A skill is a folder containing a SKILL.md file that teaches an agent a particular task or subject, alongside any scripts or reference material it needs. It packages procedural knowledge: instructions for how to get a job done.

Skills grew out of work on Claude Code, and Anthropic published Agent Skills as an open standard in December 2025. The company says more than 70 agent platforms have integrated it, including ChatGPT, Cursor, GitHub Copilot and VS Code.

What the donation includes

Anthropic is donating the Agent Skills name and logo, its GitHub organization and the agentskills.io domain. You can keep using the standard or contribute to it without joining the AAIF.

Engineers from Anthropic, Google, OpenAI and other companies will maintain the standard as individuals. Their role is individual maintenance, rather than corporate shared ownership.

Security guidance is still a proposal

Anthropic has proposed a starting roadmap covering versioned releases, a formal proposal process and security guidance for people who write and install skills. These remain proposed next steps; the donation itself does not validate the safety of individual skills.

People who want to help shape the format can give feedback on proposed specification changes through the project’s Discord.

Sources and date: 2026-10-23

Related hashtags
#GameSunakku #AI #AgentSkills #Anthropic #AAIF #AIAgents #AgenticAIFoundation

Comments

0

No login needed. Edit or delete your comment from the same browser.

All comments 0

한국어 · English · 日本語

No comments yet. Start the conversation.

Share this post

Game Sunakku에서 더 알아보기

지금 구독하여 계속 읽고 전체 아카이브에 액세스하세요.

계속 읽기