zhuyansen/agent-skills-hub

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

What it solves

It solves the difficulty of finding high-quality, compatible tools and servers for AI agents. Instead of searching through random GitHub topics, developers can find specific MCP servers, Claude Skills, and agent frameworks that are security-graded and quality-scored.

How it works

The project runs an automated pipeline every 8 hours via GitHub Actions. It collects projects from GitHub using specific queries and verified creators, cleans and classifies them into categories (like mcp-server or agent-tool), and evaluates them across six quality dimensions (such as completeness and agent readiness). A composite score is then calculated based on signals like stars, recency, and issue resolution to rank the tools. This data is served via a FastAPI backend and a React frontend.

Who it’s for

Developers building with agentic IDEs or frameworks such as Claude Code, Cursor, Windsurf, Cline, and OpenAI Codex who need to integrate external capabilities into their agents.

Highlights

  • Automated Discovery: Refreshes its directory of 117,000+ projects every 8 hours.
  • Multi-Dimensional Scoring: Ranks tools using a weighted system covering quality, momentum, and community trust.
  • Security Grading: Includes security reports to help users vet tools before installation.
  • Comparison Tools: Features side-by-side comparisons and scenario-based landing pages to find the best tool for a specific use case.

Related

  • Project
    agentregistry-dev/agentregistry

    An open-source registry for MCP servers, AI agents, skills, and prompts that centralizes discovery, management, and deployment of AI building blocks.

  • Project
    K-Dense-AI/claude-skills-mcp

    An MCP server that enables any AI assistant to discover and use Claude Agent Skills through semantic search and a performance-optimized two-package architecture.

  • Project
    affaan-m/agentshield

    A security auditor for AI agent configurations that scans Claude Code setups for secrets, permission misconfigurations, and prompt injection vectors.

  • Project
    tech-leads-club/agent-skills

    A secure, validated registry and CLI for installing verified skills and instructions to extend the capabilities of professional AI coding agents.

  • Project
    qufei1993/skills-hub

    A centralized management tool for AI agent skills that allows users to install once and sync them across dozens of different AI coding tools and devices.