Collection or directorySoftware development
open-agent-skills
Run and benchmark reusable agent skills that coordinate MCP tools.
Run and benchmark reusable agent skills that coordinate MCP tools.
Open Agent Skills is a lightweight, provider-agnostic framework for combining domain instructions with MCP tools across GitHub, filesystem, and browser tasks. It extends MCPMark with skill-based runs so developers can compare task completion and context usage under the same evaluation setup. Running it requires Python 3.11+, model credentials, and any task-specific services or containers. The project describes itself as a starting point, and some included skills remain narrowly tailored, so scripts should be reviewed before production use.
Resource types
Use cases
Runtime
Guides coding agents through clarification, planning, implementation, testing, review, and branch completion.
Run product work from discovery through review, QA, and release in Claude Code.
Protocols & integrations
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Add Vercel's official engineering skills to AI coding agents.
Install reusable skills for engineering, research, operations, marketing, and business work.