Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

A fast codebase indexer and knowledge wiki for AI agents.

Agent-first CLI for fal.ai — search, run, and manage 1000+ generative AI models

Model Context Protocol (MCP) server for AI-powered Fastly CDN management.

Touhou-inspired Agent Skills: distinct, testable, composable problem-solving workflows.

Exa MCP for web search and web crawling!

A metasearch library that aggregates results from diverse web search services

Browse the web, directly from Cursor etc.

Claude Code-style background agents for OpenCode – async delegation with context persistence

Markdown and OFM SDK w/ MCP server that transforms your Obsidian vault into an intelligent knowledge system

Magg: The MCP Aggregator

New way for collect information from the API's/Websites

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

MCP server that enables language models to interact with RDKit through natural language

Skill and tool bundles for gap (graph as policy) — Anthropic Agent Skills format, discovered by path

A framework for discovering, compiling, and validating reusable skills for scientific agents.

A Python wrapper for the Chemistry Development Kit (CDK)

LLM agents as your hyperparameter optimizer.

A comprehensive collection of Model Context Protocol (MCP) servers

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Socratic method teaching skill for Claude Code — guides users to discover answers through questioning

The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.

Claude Code skills and workflows, optimized for context-efficiency and skill quality. Skills ranging from cloud infrastructure to design to advanced maths.

Create best skills based on best books