Every plugin, skill, and MCP server for Claude Code.

Top-notch, well-written resources covering "just about everything" from core engineering domains. What's nice about this "everything-" store is most of the resources have significant standalone value and unlike some all-encompassing frameworks, although you can opt in to the author's own specific workflow patterns if you choose, the individual resources offer exemplary patterns in (just about) every Claude Code feature you can find (apologies to the Output Styles devotees).

Largest community skill library. Full SDLC framework: brainstorm → plan → TDD → review.

Extract, merge, split, rotate, OCR, fill forms.

Underlying inference engine powering most tools.

Google terminal agent. Shares skill format.

Sandboxed read/write across any folders you allow.

Fuzzy finder — pair with Claude for file picks.

Production-grade throughput.

OpenAI's Claude Code competitor. Reuses skills folder.

Cross-surface skill compilations.

A really interesting analysis of how coding agents like Claude Code are designed. It attempts to break an agent down into its fundamental parts and reconstruct it with minimal code. Great learning resource. Final product is a rudimentary agent with skills, sub-agents, and a todo-list in roughly a few hundred lines of Python.

Live library docs for 10k+ libs. Fixes outdated API hallucinations.

Rapid role-based agent prototyping.

Addresses GitHub issues by taking issue number as parameter, analyzing context, implementing solution, and testing/validating the fix for proper integration.

Feature-rich web interface.

Live tsc + eslint gating.

Lightweight Python agent lib.

Connect and unify data across various platforms and databases with [MindsDB as a single MCP server](https://docs.mindsdb.com/mcp/overview).

Network, console, performance profiling.

Smart cd replacement. Jump by partial name.

1,400+ skills via npm installer.

Production-ready: backend-architect, security-auditor, test-automator, deployment-engineer.

Programmatic prompt optimization.

This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and optimize code autonomously across recursive agent cycles.

An orchestration platform for deploying and coordinating multi-agent swarms. If I tried to go into detail it would probably crash my browser. An impressive feat of engineering that tries to cover everything and actually does a good job. Self-learning, autonomous multi-agent swarms, vector-based multi-layered memory, systematic planning, security guardrails, and so on. It's a growing project, and YMMV, but even just studying the patterns is immensely valuable, and it's clearly well-engineered.

Accessibility-tree browser automation — no screenshot guessing.

Leading Python stateful-agent framework.

📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.

51 tools for repos, issues, PRs, Actions. #1 most-used MCP (28k+ stars).

A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.

Incredibly awesome collection of resources from every category in this list, presented with a neatly polished UI, great features like usage dashboard, analytics, and everything from slash commands to hooks to agents. An awesome companion for this awesome list.

Tight GPT integration.

🐍 🏠 - A fully-featured coding agent that relies on symbolic code operations by using language servers.

A versatile configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies, such as "Introspection" and "Orchestration".

Postgres extension — simplest RAG path.

🐍 - MCP server for working with Blender

"A set of ready-to-use Agent Skills for research, science, engineering, analysis, finance and writing." That's their description - modest, simple. That's how you can tell this is really one of the best skills repos on GitHub. If you've ever thought about getting a PhD... just read all of these documents instead. Also I think it IS an AI agent or something? Awesome.

Spawn and control multiple Claude Codes in parallel from your phone or desktop. Happy Coder runs Claude Code on your hardware, sends push notifications when Claude needs more input or permission, and costs nothing.

Builds n8n workflows end-to-end from plain English (1,505 nodes).

100+ alternative subagent library.

Anthropic's 101-plugin official marketplace.

1,000+ curated skills from Anthropic, Google Labs, Vercel, Stripe, Cloudflare.

🐍 🏠 - Run Python code in a secure sandbox via MCP tool calls

Offers comprehensive development guides for three distinct AI-powered demo projects with standardized workflows, strict code style guidelines, and containerization instructions.

A very pragmatic set of well-designed agents, skills, and commands, built around a discipline of turning past mistakes and errors into lessons and opportunities for future growth and improvement. Good documentation.

Google warehouse queries.

📇 🏠 - Provide coding agents direct access to Figma data to help them one-shot design implementation.

Autonomous multi-agent coding framework for Claude Code (Claude Agent SDK) that integrates the full SDLC - "plans, builds, and validates software for you". Features a slick kanban-style UI and a well-designed but not over-engineered agent orchestration system.

Cost/token analyzer on local JSONL. Daily/monthly/session reports. Free.

232+ engineering/marketing/product/compliance skills.