---
title: "Agent Skills goes to a neutral foundation"
date: 2026-10-23
updated: 2026-10-23T00:00:00Z
url: https://arun477.github.io/feed/2026-10-23/
author: Arun Arumugam
---

# Agent Skills goes to a neutral foundation

Anthropic donated the Agent Skills standard to the Agentic AI Foundation, and Artificial Analysis revamped its coding agent benchmark, with Claude Code on Opus 5.5 in the lead.


- [Anthropic hands Agent Skills to the Linux Foundation's Agentic AI Foundation](https://www.anthropic.com/news/donating-agent-skills-to-the-agentic-ai-foundation) (Anthropic, news, Protocols, 13:41 UTC): The SKILL.md folder standard, already in 70+ agents including ChatGPT, Cursor and Copilot, moves to neutral governance like MCP did, with a roadmap for versioned releases and security guidance for installing skills.
- [Artificial Analysis Coding Agent Index v2.0: Claude Code with Opus 5.5 leads](https://x.com/ArtificialAnlys/status/2113424551396934134) (Artificial Analysis, news, Benchmarks, 13:41 UTC): The index scores model and harness pairs together across software tasks, terminal use and repo Q&A, and now swaps in Cognition's FrontierCode for DeepSWE. Claude Opus 5.5 in Claude Code tops it at 61.7.