Plugins / Skills

AI Coding Plugins and Skills

Useful third-party projects for specs, rules, agents, and repeatable web coding workflows.

Last reviewed: 2026-07-19

Design & frontend

Improve UI, UX, design systems, visual direction, and frontend implementation fidelity.

6 projects

UI UX Pro Max

A popular design skill with searchable UI styles, palettes, typography, UX guidance, and multi-framework implementation rules.

Developers who want structured design-system suggestions before an agent builds the interface.GitHub Stars109.4KSnapshot: 2026-07-24Read introduction

#02Collection

Open Design

A local-first design studio that connects skills, plugins, design systems, and MCP to coding agents.

Teams producing prototypes, dashboards, decks, images, and design-system-aware UI.GitHub Stars81KSnapshot: 2026-07-24Read introduction

#03Skill

Taste Skill

A community skill bundle for stronger layout, typography, spacing, motion, redesign audits, and anti-generic frontend output.

Codex, Claude Code, Cursor, and other agent users who want more deliberate visual output.GitHub Stars66.9KSnapshot: 2026-07-24Read introduction

#04Collection

Vercel Agent Skills

Vercel's official skills for web design review, React performance, composition, motion, and deployment.

React, Next.js, and React Native teams that want Vercel's engineering guidance inside an agent.GitHub Stars29.4KSnapshot: 2026-07-24Read introduction

#05Skill

Huashu Design

A design skill for high-fidelity prototypes, slides, motion, infographics, and structured visual critique.

Creators who want polished HTML deliverables without starting in Figma or After Effects.GitHub Stars21.9KSnapshot: 2026-07-24Read introduction

#06Skill

Hallmark

An anti-AI-slop design skill that pushes coding agents toward intentional, distinctive interfaces.

Frontend teams whose generated pages look polished but generic or interchangeable.GitHub Stars16.3KSnapshot: 2026-07-24Read introduction

Coding & implementation

Help agents implement, refactor, and navigate framework-specific or multi-file code changes.

6 projects

#01Collection

Superpowers

A high-signal Claude Code extension project for skills, workflow upgrades, and agent coding habits.

Claude Code users who want battle-tested workflow extensions.GitHub Stars260.1KSnapshot: 2026-07-24Read introduction

#02Collection

ECC

A large engineering system with skills, rules, agents, memory, security, and research-first workflows for major coding agents.

Developers who want a comprehensive, configurable coding-agent setup across languages and tools.GitHub Stars232.6KSnapshot: 2026-07-24Read introduction

#03Collection

Anthropic Skills

Anthropic's public skills repository for Claude agents: reusable workflows, document skills, and reference patterns.

Teams standardizing Claude Code, Cowork, or API agents with checked-in skills.GitHub Stars163.7KSnapshot: 2026-07-24Read introduction

#04Collection

Addy Osmani Agent Skills

Production-grade skills covering specification, planning, implementation, testing, review, performance, security, and shipping.

Teams that want one coherent engineering playbook across Codex, Claude Code, Cursor, and other agents.GitHub Stars80.1KSnapshot: 2026-07-24Read introduction

#05Plugin

Compound Engineering Plugin

Every's official plugin for planning, implementing, reviewing, and capturing reusable engineering knowledge.

Teams that want each completed feature or fix to improve future agent work.GitHub Stars23.4KSnapshot: 2026-07-24Read introduction

#06Collection

Claude Skills Collection

A broad library of engineering, product, research, compliance, and business skills with agents and commands for many coding clients.

Users who prefer browsing a large catalog and installing only the specialist capabilities they need.GitHub Stars23.1KSnapshot: 2026-07-24Read introduction

Planning, requirements & specs

Turn product intent into requirements, architecture, scoped tasks, and acceptance criteria.

7 projects

#01Skill

Grill Me

Matt Pocock's viral /grill-me skill: one-question-at-a-time interviews that stress-test a plan before any code is written.

Developers who want to surface hidden assumptions in a design or feature plan before agentic coding starts.GitHub Stars184.6KSnapshot: 2026-07-24Read introduction

#02Spec tool

GitHub Spec Kit

GitHub's toolkit for turning product intent into specifications, plans, and implementation tasks.

Teams adopting a repeatable spec-driven workflow across different AI coding agents.GitHub Stars123.5KSnapshot: 2026-07-24Read introduction

#03Skill

Caveman

A Claude Code skill that pushes terse, high-signal instructions so agents use fewer tokens without dropping task clarity.

Claude Code users who hit context or cost limits on long agent sessions and want a deliberate brevity style.GitHub Stars92.4KSnapshot: 2026-07-24Read introduction

#04Spec tool

OpenSpec

Turns product intent into specs, tasks, and implementation guidance for AI coding assistants.

Teams that want AI agents to code from explicit requirements.GitHub Stars62.3KSnapshot: 2026-07-24Read introduction

#05Workflow

BMAD-METHOD

A structured method for AI-driven product, architecture, development, and delivery roles.

Vibe coding projects that need more structure before they grow.GitHub Stars51KSnapshot: 2026-07-24Read introduction

#06Workflow

Task Master

An AI-powered task-management workflow that decomposes requirements for coding assistants and IDE agents.

Projects that need a durable task graph instead of a one-shot implementation prompt.GitHub Stars27.9KSnapshot: 2026-07-24Read introduction

#07Skill

Planning with Files

A file-based planning skill for long-running agent tasks that must survive context loss, restarts, and collaboration.

Complex tasks where progress, decisions, and completion evidence must persist outside the chat window.GitHub Stars25.7KSnapshot: 2026-07-24Read introduction

Testing, review & quality

Strengthen testing, debugging, code review, security checks, and delivery verification.

6 projects

#01MCP server

Playwright MCP

Microsoft's Playwright MCP server for browser automation through structured accessibility snapshots and deterministic tools.

Coding agents that need repeatable browser inspection, interaction, debugging, and acceptance testing.GitHub Stars35.4KSnapshot: 2026-07-24Read introduction

#02Plugin

Codex Plugin for Claude Code

OpenAI's plugin for invoking Codex from Claude Code to review code, delegate work, rescue a task, or transfer context.

Claude Code users who want an independent Codex pass without leaving their current session.GitHub Stars29.8KSnapshot: 2026-07-24Read introduction

#03Collection

Cybersecurity Skills

A large community collection of structured cybersecurity skills mapped to major security and AI-risk frameworks.

Security teams and developers who need structured threat, defense, compliance, and AI-risk playbooks inside agents.GitHub Stars26.4KSnapshot: 2026-07-24Read introduction

#04MCP server

Code Review Graph

A local-first MCP and CLI that builds a persistent code graph so reviewers and agents can load only relevant context.

Large repositories where reviews fail because relationships and impact are hard to see.GitHub Stars25.9KSnapshot: 2026-07-24Read introduction

#05Workflow

NVIDIA SkillSpector

NVIDIA's scanner for detecting vulnerabilities, malicious patterns, and risky behavior in AI agent skills.

Teams reviewing third-party skills before installing or distributing them.GitHub Stars13.6KSnapshot: 2026-07-24Read introduction

#06Workflow

PR-Agent

An open-source AI reviewer for describing, reviewing, improving, and answering questions about pull requests.

Teams that want automated review assistance across GitHub, GitLab, Bitbucket, Azure DevOps, or Gitea.GitHub Stars12.2KSnapshot: 2026-07-24Read introduction

Agent orchestration & automation

Coordinate agents, persistent tasks, parallel work, and repeatable development workflows.

6 projects

#01Plugin

gstack

A Claude Code plugin with opinionated product, design, engineering-management, release, documentation, and QA roles.

Founders and small teams that want forceful reviews across the full product-development loop.GitHub Stars124KSnapshot: 2026-07-24Read introduction

#02Workflow

oh-my-openagent

A popular agent harness for complex codebases, project memory, planning, execution, and verified completion.

Codex, OpenCode, and terminal-agent users who want a stronger coding loop.GitHub Stars66.5KSnapshot: 2026-07-24Read introduction

#03Workflow

Ruflo

A meta-harness for coordinating agent swarms, autonomous workflows, memory, learning, RAG, and coding-agent integrations.

Advanced teams experimenting with multi-agent coordination and persistent autonomous workflows.GitHub Stars65.7KSnapshot: 2026-07-24Read introduction

#04Collection

wshobson/agents

A multi-harness marketplace of specialized agents and plugins for coding, architecture, testing, security, and operations.

Users who want to assemble a specialist agent team instead of relying on one general-purpose persona.GitHub Stars38.2KSnapshot: 2026-07-24Read introduction

#05Plugin

oh-my-claudecode

Multi-agent orchestration for Claude Code with team mode, autopilot, Ralph, Ultrawork, skills, and provider advisors.

Claude Code users who want stronger autonomous execution and parallel review.GitHub Stars38KSnapshot: 2026-07-24Read introduction

#06Collection

Awesome Claude Code Subagents

A curated collection of more than one hundred specialized Claude Code subagents across development disciplines.

Claude Code users who want ready-made specialist personas rather than designing agents from scratch.GitHub Stars23.6KSnapshot: 2026-07-24Read introduction

Context, rules & integrations

Connect project rules, memory, MCP servers, external tools, and durable context to coding agents.

7 projects

#01Workflow

Hermes Agent

Nous Research’s open agent stack that keeps context, tools, and workflows across sessions instead of resetting every chat.

Developers who want a long-running coding agent with integrations, memory, and room to grow custom skills.GitHub Stars219.5KSnapshot: 2026-07-24Read introduction

#02Skill

Graphify

An AI coding skill that turns code, schemas, infrastructure, documents, and media into a queryable knowledge graph.

Large or unfamiliar repositories where agents need relationships across code, data, and infrastructure.GitHub Stars94.6KSnapshot: 2026-07-24Read introduction

#03Collection

Awesome MCP Servers

A high-Star curated directory of Model Context Protocol servers organized by capability and integration domain.

Users discovering external tools and data sources to connect to MCP-compatible coding agents.GitHub Stars91.3KSnapshot: 2026-07-24Read introduction

#04MCP server

MCP Servers

Official Model Context Protocol server collection for filesystem, git, browser, memory, and tool integrations.

Developers wiring Claude Code, Cursor, Codex, or custom agents to external tools via MCP.GitHub Stars88.8KSnapshot: 2026-07-24Read introduction

#05Rules

Awesome CursorRules

A large collection of Cursor rule examples for frameworks, languages, and project habits.

Cursor users who want better default behavior for web projects.GitHub Stars40.4KSnapshot: 2026-07-24Read introduction

#06Collection

Awesome Copilot

GitHub's community collection of Copilot instructions, agents, skills, and configuration examples.

Teams using GitHub Copilot who want reusable prompts, agents, and repo-level instructions.GitHub Stars37KSnapshot: 2026-07-24Read introduction

#07MCP server

GitHub MCP Server

GitHub's official MCP server for giving compatible agents structured access to repositories, issues, pull requests, and workflows.

Teams that want agents to work with GitHub through explicit tools and repository permissions.GitHub Stars31.7KSnapshot: 2026-07-24Read introduction