← all releases
Vercel·Jan 1, 2026·v1.0·open source

Agent Skills

Agent Skills is an open-source repository developed by Vercel that provides a collection of modular packages, known as 'skills,' designed to enhance the capabilities of AI agents. These skills are structured as folders containing instructions, scripts, and resources that agents can dynamically load to perform specialized tasks more effectively.

featured on blogAI AgentsInfrastructureML
visit website
on the blogMeet Agent Plugins: A New Open Standard That Unifies Agent Skills and MCP Servers in a Shared Format 5 min
overview

Agent Skills is an open-source repository developed by Vercel that provides a collection of modular packages, known as 'skills,' designed to enhance the capabilities of AI agents. These skills are structured as folders containing instructions, scripts, and resources that agents can dynamically load to perform specialized tasks more effectively.

key features
  • 01Modular skill packages for AI agents
  • 02Dynamic loading of skills to improve task performance
  • 03Open-source repository for community contributions
related productsbrowse all →
AIO Sandboxopen sourceAIO Sandbox is an integrated environment designed for AI agents, combining a browser, terminal, filesystem, VSCode, Jupyter, and MCP Server into a single Docker container. This unified setup allows seamless development and execution of AI agents without the need for multiple services.SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.