AgentSkillsHub — 70K Claude Skills & MCP Servers, Searchable

Source: https://agentskillshub.top/

Browse by Category

All tools are organized into categories based on their primary function. From MCP servers that extend AI coding agents to prompt libraries and full agent frameworks, find exactly what you need.

• MCP Server (https://agentskillshub.top/category/mcp-server/) — Model Context Protocol servers for AI agents
• Claude Skill (https://agentskillshub.top/category/claude-skill/) — Skills and plugins for Anthropic Claude
• Codex Skill (https://agentskillshub.top/category/codex-skill/) — Skills for OpenAI Codex agents
• Agent Tool (https://agentskillshub.top/category/agent-tool/) — General-purpose AI agent utilities
• Prompt Library (https://agentskillshub.top/category/prompt-library/) — Curated prompt collections and templates
• AI Coding Assistant (https://agentskillshub.top/category/ai-coding-assistant/) — AI-powered code generation and editing tools
• AI Tool (https://agentskillshub.top/category/uncategorized/) — Other open-source AI tools

Popular Scenarios

Explore curated collections of the best tools for common AI agent workflows. Each scenario page ranks tools by quality score, stars, and community activity to help you find the right solution for your use case.

• MCP Browser Automation (https://agentskillshub.top/best/mcp-browser/)
• MCP Database Tools (https://agentskillshub.top/best/mcp-database/)
• Code Review (https://agentskillshub.top/best/code-review/)
• AI Agent Frameworks (https://agentskillshub.top/best/ai-agent-framework/)
• Web Scraping (https://agentskillshub.top/best/web-scraping/)
• Workflow Automation (https://agentskillshub.top/best/workflow-automation/)
• Browser Automation (https://agentskillshub.top/best/browser-automation/)
• Code Completion & Generation (https://agentskillshub.top/best/code-completion/)
• Security Auditing (https://agentskillshub.top/best/security-audit/)
• Prompt Engineering (https://agentskillshub.top/best/prompt-engineering/)

AgentSkillsHub indexes over 55,000 open-source repositories across MCP servers, Claude skills, Codex skills, AI coding assistants, and agent tools. Every project is scored on 10 weighted signals including GitHub stars, code quality, documentation, and community activity. Data refreshes every 8 hours so you always see the latest tools.

Quality Scoring

Each tool receives a composite quality score from 0 to 100 based on six dimensions: completeness, clarity, specificity, examples, README structure, and agent readiness. This helps developers quickly identify production-ready tools versus experimental projects.

Compare and Discover

Use the Compare feature to evaluate multiple tools side by side. The Skill Analyzer provides security grades and platform compatibility checks, helping teams make informed decisions about which open-source AI tools to adopt.

How It Works

Agent Skills Hub automatically discovers AI agent tools from GitHub using multi-phase data collection. Each repository goes through search, enrichment, README analysis, and quality scoring. Our system tracks stars, forks, commit frequency, open issues, documentation quality, and community engagement to produce a single composite score. New tools appear within hours of being published. Developers can browse by category, search by keyword, filter by programming language, or explore curated scenario pages like browser automation, code review, and database management.

Stay Updated

Subscribe to the weekly newsletter for trending AI agent tools, new MCP servers, and top skill picks delivered to your inbox every Monday. Join thousands of developers who rely on AgentSkillsHub to stay current with the fast-moving AI agent ecosystem. Each issue features the top new tools of the week, star velocity rankings, and curated recommendations across all categories.

About the Editor

AgentSkillsHub is built and maintained by Jason Zhu (), an independent researcher tracking open-source AI agent ecosystems since 2024. Jason is also the author of the Blue Book of Agent Skills 2026 (https://github.com/zhuyansen/skill-blue-book), an in-depth analysis of the Claude Skills / MCP / Codex ecosystem published openly on GitHub.

The Hub runs as a solo project, designed to be transparent and reproducible: every scoring dimension is documented, every data snapshot is archived, and the entire source code is open under MIT on GitHub (https://github.com/ZhuYansen/agent-skills-hub). The goal is not to rank skills by popularity alone, but to help developers find tools that are actually production-ready.

Editorial Methodology

Every indexed repository passes through a 6-phase pipeline running every 8 hours: GitHub search → metadata enrichment → README fetch → quality scoring (10 weighted dimensions) → category classification → composability analysis. No manual curation is applied to ranking — signals are purely data-driven to avoid editorial bias.

Daily reports of new skills and weekly trending lists are selected according to transparent rules documented in the repository. When human judgement is needed (such as for “Verified Creator” decisions), the reasoning and criteria are written down publicly, not hidden behind a pay-for-placement system.

Jason Zhu (@GoSailGlobal): I built Agent Skills Hub in less than three days (Happy Women’s Day 👀) https://t.co/KqpGzgPl3x

Why did I build this product? 1️⃣ To help people find the right skills among the many available — features like categories, recent updates, and weekly rankings solve the problem of finding quality skills 2️⃣ To find the right people: the top skill creators