Discover the Best
Claude Skills & MCP Servers

Official Microsoft .NET team skill library for AI coding agents. 12 specialized plugins — 80+ granular skills — covering .NET core development, Entity Framework data access, performance diagnostics with dotnet-trace, MSBuild optimization, NuGet package management, migration from .NET Framework, MAUI mobile development, Semantic Kernel AI integration, and testing patterns. Eliminates the hallucinations AI tools produce when generating .NET-specific code.

Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, Gemini, and other AI agents. Instead of repeatedly grepping and reading files, CodeGraph parses your codebase once into a structured map of functions, classes, imports, and call relationships — so agents navigate with fewer tool calls and far less token spend. Supports 19+ languages, works 100% locally, integrates via CLI, MCP, or Agent Skill.

A single CLAUDE.md file distilling Andrej Karpathy's observations on LLM coding pitfalls into 4 hard rules: think before coding, prefer simplicity over abstraction, make targeted changes only, and verify by outcome not intent. Packaged as a proper Agent Skill with .cursor/rules, plugin.json, and multi-tool support. 140K stars — the fastest validation that developers already knew AI was doing these things wrong.

A meta-tool that converts any document, GitHub repository, or PDF into a ready-to-use agent skill. Point it at a codebase README, an API specification, a technical paper, or a company wiki — Skill Seekers analyzes the content and generates a properly structured SKILL.md that encodes the knowledge as an installable skill. Particularly useful for teams who want to turn internal documentation into AI-accessible skills without writing them from scratch.

The official skills directory maintained by OpenAI for use with Codex CLI and compatible AI coding assistants. Created in late 2025 as OpenAI's answer to Anthropic's skills ecosystem, it provides reference implementations for common development workflows — code review, testing, documentation, and deployment. As the second major AI lab to adopt the SKILL.md standard, OpenAI's entry signals that agent skills are becoming a universal interface for AI-assisted development.

The official specification repository for the Agent Skills open standard — the SKILL.md format that powers cross-platform AI agent skill interoperability. Maintained by the agentskills organization, this repo defines how skills should be structured, what metadata is required, and how agents should discover and invoke skills. If you're building skills for distribution, this is the authoritative reference. The standard is now adopted by Claude Code, Codex CLI, Cursor, Gemini CLI, and 30+ other tools.

Official agent skills from Vercel, the team behind Next.js and the world's largest frontend deployment platform. Covers deployment automation, serverless function optimization, edge computing patterns, and Next.js-specific workflows. Each skill is production-tested across Vercel's own infrastructure. Particularly valuable for teams building on the Vercel platform — these skills encode the same deployment patterns Vercel uses internally.

The community's most comprehensive Claude Code resource guide. 86+ real-world tips, tricks, and best practices collected from developers who use Claude Code daily — covering skills, agents, hooks, commands, and workflows. Unlike official documentation, this is battle-tested knowledge from practitioners: what actually works, what to avoid, and how to get the most out of Claude Code on complex projects. Actively maintained with contributions from engineers at major tech companies.