5,123 boosters — open source, verified from GitHub, ready to install
"name": "norman-finance", "description": "AI-powered bookkeeping and tax filing automation for entrepreneurs at the heart of the European economy. Connect to Norman to manage clients, invoices, transactions, taxes, and documents.", "name": "Norman Finance",
Trade on Lighter — a ZK-rollup perpetual futures and spot exchange. Scripts live in this skill's directory. Read commands use , write commands use . Every command prints structured JSON to stdout. Errors are always in JSON as . Commands use syntax mirroring the Lighter UI (e.g. , , ).
Subagents enable deep agents to delegate work while maintaining clean context. They're useful for context quarantine and providing specialized instructions. Subagents solve the context bloat problem. When agents use tools producing large outputs (web searches, file reads, database queries), the cont
"name": "buildable", "description": "Local product-structure compiler, compact UI/UX brain, and quality gate for your coding agent. A prompt becomes the right archetype, selected design system, runnable build-verified starter, and reviewed result while loading only the references each prompt needs."
LinkedIn MCP Server enables Claude to interact with LinkedIn data and functionality through the Model Context Protocol. Developers building AI assistants that need LinkedIn integration will find this valuable.
"description": "Prose linter and editor skill. /pilcrow audit, polish, humanize, tighten, clarify, pace, lead, verify, aloud, argue, plus teach/document/craft. AI-tell detection is one feature among many.", "version": "0.17.2", "name": "Samuel Galanakis"
"description": "Adaptive UI component library as part of Serendie Design System by Mitsubishi Electric", "author": { "name": "SerendieDesign" }, "homepage": "https://serendie.design",
Agents merge language models with tools to build systems capable of reasoning about tasks, deciding which tools to suit the situation, and iteratively working toward solutions. The function provides a production-ready implementation. Agents follow a loop pattern: input flows to the model, which dec
"name": "workflow-audit", "description": "SwiftUI workflow audit — find dead ends, broken promises, and UX friction. Bundled with a phased plan generator.", "name": "Terry Nyberg"
This Cursor rule set enables persistent memory and lesson management by integrating with an MCP server, automatically tracking user identity, preferences, goals, and past errors to provide contextually-aware assistance. Developers using Cursor who need continuity across sessions and automated error pattern recognition will benefit most.
An MCP server integration for Upstash that enables Claude to interact with Upstash services (Redis, Kafka, QStash) directly. Developers building applications that need serverless data and messaging infrastructure benefit from this seamless Claude integration.
If no interval is specified, the default interval is 10 minutes. The loop stops automatically when any of the following occur: 1. Maximum iteration count (100) is reached
You are a biomedical data visualization expert powered by the Bizard atlas — a comprehensive collection of 256 reproducible visualization tutorials covering R, Python, and Julia, with 793 curated figure examples from real biomedical research. When a user asks for help with data visualization — espec
Copilot instructions for developing and maintaining a Go application that syncs reading progress and book metadata between AudiobookShelf and Hardcover platforms. Developers building or contributing to this sync tool benefit from clear architectural guidance and API integration patterns.
Matchms is a Python library for mass spectrometry data processing, enabling researchers to load spectral data from multiple formats, standardize metadata, calculate spectral similarities, and identify compounds for metabolomics workflows.
"description": "MCP server for Android Debug Bridge (ADB) interactions in TypeScript", "main": "dist/index.js", "adb-mcp": "dist/index.js"
当用户请求涉及以下任一主题时使用本 skill： 使用本 skill 处理任务时，优先输出：
"name": "@pan-sec/notebooklm-mcp", "version": "2026.2.11", "mcpName": "io.github.Pantheon-Security/notebooklm-mcp-secure",
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
"name": "brainstorm-mcp", "mcpName": "io.github.spranab/brainstorm-mcp", "description": "MCP server for multi-round AI brainstorming debates across multiple models",
에이전트 기반 작업 오케스트레이션 스킬. Plan→Work→Review 사이클로 구조화된 작업 수행. 브릿지가 에이전트 상태를 실시간으로 추적하고 채널에 알림을 전송합니다. 에이전트 프롬프트를 읽어서 에 전달:
"name": "journalism-toolkit", "description": "30 specialized journalism agents for investigative reporting, fact-checking, disinformation analysis, AI content detection, foreign news de-biasing, bot & troll detection, multimedia production, and content distribution", "name": "Contributors"
"name": "diff-fox-marketplace", "name": "mthooyavan", "email": "mthooyavan@users.noreply.github.com"
gomcp provides a Go implementation of the Model Context Protocol to enable AI agents in Cursor to interact with external tools and resources through a standardized interface. Developers using Cursor who need to extend AI capabilities with custom integrations benefit from this protocol implementation.
