What is Open Agent Skill?

Open Agent Skill is an open marketplace for AI agent skills. It helps developers discover, publish, and share reusable skills, tools, plugins, and workflows for AI agents like Claude, GPT, and LangChain.

How do I install a skill?

You can install any skill using the command: npx skills add . Each skill page also shows specific installation instructions.

How are skills ranked?

Skills are ranked by real agent usage data, not just GitHub stars. We track actual API calls from agents, success rates, and response times to surface the most reliable skills.

How do I submit my own skill?

Visit the Submit page and provide your GitHub repository URL. Our AI will review your skill for quality and security, then it will be listed in the marketplace.

Decision filters

Choose skills by scenario, quality, and trust signals.

Use casePlatform fitQuality tierGitHub adoption

6 skills matching "benchmarking"

Best blend of quality, stars, freshness, and agent usage

AutoRAG

VERIFIEDEXCELLENT · 100

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

$ npx skills add Marker-Inc-Korea/AutoRAG

4.8K stars67 qualityClaude Code

High-confidence pick with strong adoption and healthy maintenance signals.

pythonrag

by Marker-Inc-KoreaQuick view

Evalscope

VERIFIEDEXCELLENT · 100

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

$ npx skills add modelscope/evalscope

2.8K stars66 qualityClaude Code

High-confidence pick with strong adoption and healthy maintenance signals.

pythonrag

by modelscopeQuick view

Agentops

VERIFIEDEXCELLENT · 100

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

$ npx skills add AgentOps-AI/agentops

5.6K stars65 qualityClaude Code + OpenAI Agents

High-confidence pick with strong adoption and healthy maintenance signals.

pythonllm

by AgentOps-AIQuick view

Awesome Web Agents

VERIFIEDEXCELLENT · 98

🔥 A list of tools, frameworks, and resources for building AI web agents

$ npx skills add steel-dev/awesome-web-agents

1.4K stars64 qualityClaude Code + Browser agents

High-confidence pick with strong adoption and healthy maintenance signals.

pythonbrowser-automation

by steel-devQuick view

Docext

VERIFIEDEXCELLENT · 98

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

$ npx skills add NanoNets/docext

2.0K stars62 qualityClaude Code

High-confidence pick with strong adoption and healthy maintenance signals.

pythonrag

by NanoNetsQuick view

WindowsAgentArena

STRONG · 81

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

$ npx skills add microsoft/WindowsAgentArena

861 stars51 qualityClaude Code

Solid option that is likely worth shortlisting for production workflows.

pythonai-agents

by microsoftQuick view