AIsaAIsaStudio 中文 Open AIsa Studio

Anthropic Donates Agent Skills Standard to the Agentic AI Foundation

Original title: Donating Agent Skills to the Agentic AI Foundation \ Anthropic

Anthropic announced it is donating the Agent Skills open standard to the Agentic AI Foundation (AAIF) under the Linux Foundation, which it co-founded with Block and OpenAI and which already houses MCP. Since the standard's publication in December 2025, more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot, and VS Code, have integrated Agent Skills. A skill is a folder with a SKILL.md file plus scripts or reference material that teaches an agent a specific task or domain; the concept emerged from work on Claude Code, and within weeks of its October 2025 launch developers published thousands of skills on GitHub and wrote loaders for Codex, Cursor, and OpenCode.

Why it matters

The donating party explains the new governance home and community role for the Agent Skills standard, useful context for where the standard is headed.

Read the original ↗AI Daily, Oct 23

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Analysis

What happened

Anthropic announced it is donating Agent Skills, an open standard that gives AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF). AAIF operates under the Linux Foundation and was co-founded by Anthropic with Block and OpenAI; Anthropic previously donated the Model Context Protocol (MCP) to the same foundation. The donation covers the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain.

Key details

  • A skill is deliberately lightweight: 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.
  • The concept originated in work on Claude Code. Anthropic says Claude Code handled general knowledge work well but 「often lacked the procedural knowledge that real business tasks need.」
  • Within weeks of the October 2025 launch, developers published thousands of skills on GitHub and wrote loaders for Codex, Cursor, and OpenCode.
  • Since the standard was published in December 2025, more than 70 agent platforms have integrated it, including ChatGPT, Cursor, GitHub Copilot, and VS Code. So far, 1 million skills have been published and nearly 280 million installed.
  • Maintenance: engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers. Users can keep using or contributing to the standard without joining AAIF.
  • The proposed roadmap includes versioned releases, a formal proposal process, and security guidance for people who write and install skills; feedback on specification changes is collected via Discord.

Why it matters

This is Anthropic's second transfer of an agent-infrastructure standard to a neutral foundation, following MCP, consistent with its stated commitment to keeping the standard "open, community-driven, and vendor-neutral." Handing over the name, logo, GitHub organization, and domain means governance of Agent Skills is no longer controlled by a single vendor, and the community has a say in where the standard goes next. With more than 70 integrating platforms—including OpenAI's ChatGPT—and installations in the hundreds of millions, the standard has become a de facto cross-vendor channel for distributing agent capabilities; joint maintenance by engineers from multiple companies as individuals reduces the risk of the standard being captured by one commercial interest. The addition of versioned releases, a formal proposal process, and security guidance marks its move from a vendor project into formal specification governance.

Who it affects

  • Agent platform developers: with the standard under a neutral foundation, the path for integration and contribution is clearer, but specification evolution should be tracked through upcoming versioned releases and the proposal process.
  • Skill authors and users: the security guidance relates directly to writing and installing skills; existing usage is unaffected and joining AAIF is not required.
  • Teams watching the MCP ecosystem: with Agent Skills and MCP both under AAIF, governance coordination between the two may shape the broader agent-infrastructure landscape.
Original article

Today, we’re donating Agent Skills, the open standard that gives AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF). More than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot, and VS Code, have integrated Agent Skills since we published the standard in December 2025.

Agent interoperability through simplicity

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. We developed skills while working on Claude Code. It handled general knowledge work well, but often lacked the procedural knowledge that real business tasks need. Within weeks of our October 2025 launch, developers published thousands of skills on GitHub and wrote loaders for Codex, Cursor, and OpenCode. We then published Agent Skills as an open standard, under its own GitHub organization and domain, so any agent could use it. So far, 1 million skills have been published and nearly 280 million installed.

Donating Agent Skills to AAIF

We’re committed to keeping Agent Skills open, community-driven, and vendor-neutral. Today, we are donating the standard to the Agentic AI Foundation (AAIF) under the Linux Foundation, which we co-founded with Block and OpenAI last year, and to which we donated the Model Context Protocol (MCP). The AAIF will provide a neutral home to the standard going forward, ensuring the community has a say in where Agent Skills go next.

We are donating the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain. You can continue to use the standard or contribute to it without joining the AAIF.

Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers.

What comes next

We’ve proposed starting with a roadmap covering versioned releases, a formal proposal process, and security guidance for people who write and install skills. As with MCP, the project will continue to prioritize community input and transparent decision-making. You can join the project’s Discord to give feedback on proposed specification changes.

Thank you to the developers who built with Agent Skills from the start, and to the teams who brought skills into their products. Read the specification at agentskills.io and join the discussion on GitHub.

The original belongs to 官方博客 · Anthropic / Meta / xAI and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 1