Anthropic donates Agent Skills to the Agentic AI Foundation: the AI coding 'skills' format is now vendor-neutral

On 22 October 2026 Anthropic donated the Agent Skills standard to the Linux Foundation's Agentic AI Foundation. Over 70 AI agent platforms, including Cursor, GitHub Copilot and VS Code, already support it, so AI-assisted development workflows are less tied to one vendor.

On 22 October 2026 Anthropic announced it is donating Agent Skills to the Agentic AI Foundation (AAIF), which sits under the Linux Foundation. Anthropic co-founded the AAIF with Block and OpenAI, and it already hosts the Model Context Protocol (MCP).

What a skill is

A skill is a folder containing a SKILL.md file, plus any scripts or reference material. It packages specialist knowledge and a repeatable workflow so an AI agent can follow it: how your team writes tests, how your app is deployed, what your brand rules are. Anthropic says the donation covers the standard itself, the name and logo, the GitHub organisation and the agentskills.io domain.

The numbers

Anthropic reports that more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot and VS Code, have integrated the standard since it was published in December 2025. It cites about 1 million skills published and nearly 280 million installs. Maintainers from Anthropic, Google, OpenAI and others will look after it as individuals, and the roadmap includes versioned releases, a formal proposal process and security guidance for people who write and install skills.

What it means

The standard being owned by a neutral foundation, not one vendor, matters more than the headline. A team that writes its engineering rules once as skills can, in principle, use them across several AI coding tools. That lowers the cost of switching tools, which is useful in a market where models and pricing change every few weeks.

The security note is the other half. Skills carry instructions and scripts that an agent will run, so installing one is closer to installing software than downloading a document.

So what

If you commission software from a team that uses AI coding tools, ask whether their working rules are written down in a portable form, and who reviews third-party skills before they are installed. Portable, reviewed conventions are part of what separates disciplined AI-assisted development from improvised prompting. If you are planning a build and want to know how we run it, start a project.

← All research

More research.

Custom application development vs custom app development: two searches, two different buyers

Buyers search for both 'custom application development' and 'custom app development', and the two phrases usually mean different projects. Knowing which one you need changes the brief, the team and the quote.

Read ›

GitHub's Copilot metrics now count OpenCode and Claude Code traffic: who really uses which AI coding tool

On 23 October 2026 GitHub added a per-tool breakdown to the Copilot usage metrics API, so tools such as OpenCode and Claude Code are counted even without editor telemetry. It shows how mixed the AI coding tool stack inside software teams has become.

Read ›

GitHub Copilot retires Claude Opus 5 and GPT-5.6 Terra on 16 November: the model-churn bill for buyers

GitHub has announced that Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra leave every Copilot experience on 16 November 2026. For anyone commissioning AI-assisted development, model retirement is now a monthly event to plan around.

Read ›

GitHub Copilot now benchmarks how 'agent-first' your developers are against your industry

On 22 October 2026 GitHub added opt-in industry comparisons to its Copilot impact dashboard, ranking firms by share of agent-first developers and by the merge rate of agentic pull requests. Here is how to read the numbers when you are buying software.

Read ›

Apple's new bait-and-switch rule 2.5.19: what it means for AI-built and fast-shipped apps

On 16 October 2026 Apple updated its App Review Guidelines: apps that change after approval can be removed from the App Store and the Developer Program, and AI-generated intimate imagery is now explicitly covered. Here is what founders commissioning an iOS app should check.

Read ›

GitHub Copilot agentic autofix is generally available: AI now fixes security alerts, and bills for it

GitHub made agentic autofix for code scanning alerts generally available on 15 October 2026. Copilot can now fix up to 25 security alerts in one pull request, using AI credits your supplier or your team pays for.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work