490 boosters for "agents" — open source, verified from GitHub, ready to install
A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed website analysis with 13+ specialized tools.
Pipeline for downloading academic paper full-text at scale. Handles the three classes of sources that exist in 2026: 1. Publisher TDM APIs (Elsevier / Wiley / Springer) — for paywalled content where the institution has a subscription 2. OA aggregators (Unpaywall / OpenAlex / Crossref) — for Open Acc
"name": "quarkus-agent", "description": "MCP server for AI coding agents to create, manage, and interact with Quarkus applications. Provides tools for project scaffolding, dev mode lifecycle, extension skills, Dev MCP proxy, and documentation search.", "url": "https://quarkus.io"
"name": "openaccountant-skills", "description": "Open Accountant financial skills — P&L reports, budgeting, tax prep, debt payoff, and more for AI agents",
"name": "dcode-agent-kit", "description": "Scaffold a Deep Agents (LangChain) agent or a dcode CLI agent from one command (/new-dcode-agent). The agents it builds work with any OpenAI-compatible provider.", "author": { "name": "Elia Alberti" },
"name": "apollo-skills", "description": "Agent skills for AI coding agents working with Apollo GraphQL tools and technologies", "name": "Apollo GraphQL",
"name": "wigtn-plugins", "description": "AI-native Vibe Coding — From idea to Deploy, Zero friction. Unified plugin with 13 agents, 5 commands, 5 skills, team-based parallel build, 20 design styles.", "name": "WIGTN Crew",
"description": "Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 23 hook scripts, auto-learning pipeline, hook profiles, and multi-language coding standards", "name": "xiaobei930", "url": "https:
"name": "amplihack", "description": "AI-powered development framework with specialized agents and automated workflows for Claude Code", "name": "Microsoft Amplihack Team",
"description": "iMessage integration for Claude Code - read messages, send replies, and run autonomous agents via iMessage", "name": "David Siegel", "email": "djsiegel@gmail.com"
"name": "design-system-ops", "description": "Staff-level design system auditing, governance, documentation, validation, and communication — 39 skills, 4 agents, and 11 knowledge notes for the full design system lifecycle", "name": "Murphy Trueman"
Blockscout MCP Server enables AI agents and automation tools to query blockchain data directly, including account balances, transaction history, and smart contract interactions. Developers building AI-powered blockchain applications, trading bots, and automation tools benefit from seamless blockchain data access.
"description": "Atelier plugin marketplace" "name": "tricorder", "source": "./.claude-plugin/tricorder",
"displayName": "Darkroom Engineering", "description": "Darkroom Engineering AI coding standards. Layered config with portable AGENTS.md, progressive complexity, and two-tier knowledge system.", "version": "13.2.2",
A layered backend architecture ruleset for Go/TypeScript projects that enforces clean dependency patterns (core → infra → database/permission → server) to maintain code organization and testability in internal tools. Ideal for teams building admin dashboards and CRUD applications who need consistent architectural guidance.
"name": "safari-mcp", "mcpName": "io.github.achiya-automation/safari-mcp", "description": "Safari browser automation for AI agents — native macOS, zero Chrome overhead. 80 tools via AppleScript + JavaScript.",
1. 架构不是「画」出来的,是从约束里「逼」出来的。 没搞清约束就画图,画什么都是瞎画。 2. 没有银弹,只有取舍。 任何决策本质都是「用 A 换 B」。一个「没有缺点」的方案,不是完美,是没想清楚。 3. 没有「最好的架构」,只有「在这组约束下最合适的架构」。 同样是聊天,内部工具和微信的答案天差地别。
This MCP server enables AI coding agents to analyze test coverage from LCOV files, making them coverage-aware while optimizing token usage. It's valuable for developers using Claude Desktop or Code who want to improve code quality by integrating coverage insights into their AI-assisted workflows.
"name": "claude-brain-sync", "description": "Sync and evolve your Claude Code brain across machines. Automatically exports, merges, and applies your accumulated knowledge (memory, skills, agents, rules, settings) across all your development machines via Git.", "url": "https://github.com/toroleapinc"
"description": "Prefect workflow orchestration - read-only MCP server for diagnostics, CLI skill for mutations", "name": "Prefect Technologies", "email": "help@prefect.io",
"description": "Look up the public API of any JVM dependency (Scala 3, Scala 2, Java) from the terminal", "repository": "https://github.com/virtuslab/cellar", "license": "MPL-2.0"
"name": "skill-git", "description": "Version control system for Claude Code agent skills — git for SKILL.md files", "keywords": ["skills", "version-control", "git", "agent"]
A structured prompt booster for Windsurf that establishes best practices for agentic workflows, covering instruction handling, task analysis, implementation verification, and a complete tech stack (Next.js, Payload CMS, TypeScript). It helps developers build reliable AI-powered applications with clear guidelines and quality standards.
"name": "ultraship", "description": "Claude Code plugin — 36 tools, 42 skills, 12 agents. Elite SEO strategy with AI traffic tracking, IndexNow, GSC-GA4 cross-reference, CTR anomalies, brand filtering, keyword intelligence, index doctor, pentest, ship, launch, grow, rescue.", "name": "Houseofmvps",
