Cursor Install Guide

AS

aytzey/showagent

Developer tools

Find local coding-agent sessions and copy their user and assistant messages into another agent's native format. TUI, CLI and MCP.

DW

daidaij/websearch-mcpserver

Developer tools

一个轻量的ai websearch的自建个人方案，支持baidu / tavily / exa / anysearch / doubao api（支持池化使用）, bing/ddg 和学术搜索引擎

MK

manufosela/karajan-code

Developer tools

Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code review. Supports Claude, Codex, Gemini, OpenCode and Aider.

NW

nightnei/wordpress-developer-mcp-server

Developer tools

Build WordPress sites with your AI

HC

hugoguerrap/crypto-claude-desk

Developer tools

Multi-agent cryptocurrency intelligence system built with Claude Code. 6 AI agents, 66 MCP tools, Agent Teams, zero orchestration code.

RM

regismesquita/mcp_a2a

Developer tools

A2A MCP Server is a lightweight Python bridge that lets Claude Desktop or any MCP client talk to A2A agents.

WL

wulawulu/learn-claude-code-rs

Developer tools

A progressive AI Agent Harness tutorial written in Rust.

LM

ltc6539/mcp-ppt

Developer tools

This MCP server enables dynamic creation, editing and saving of PowerPoint presentations. Built upon the MCP and using the python-pptx library, it provides a flexible interface to add slides, images,...

HT

healthymind-tech/taiwan-health-mcp

Developer tools

台灣醫療健康資料整合 MCP 伺服器 整合 ICD-10-CM/PCS、SNOMED CT、LOINC、台灣 FDA 藥品 / 健康補充品 / 食品營養，以及 FHIR R4 IG 授權與驗證工具

RA

recallium-ai/recallium

Developer tools

Your digital developer twin — because "explain our setup again" gets old fast.

SA

sinewaveai/agent-security-scanner-mcp

Developer tools

Run it before Claude Code, Cursor, Windsurf, Cline, OpenCode, or another agent trusts new code, tools, prompts, or dependencies.

PM

pvliesdonk/markdown-vault-mcp

Developer tools

Generic markdown vault MCP with hybrid search

AH

alchaincyf/huashu-md-html

API development

md/html 双向流水线 · 三个能力一站式：万物→md / md→精美html / html→md。封装 markitdown + Pandoc + html-to-markdown + trafilatura。4 套反 AI slop 主题。Claude Code skill.

PC

public-clis/bilibili-cli

Developer tools

A CLI for Bilibili — browse videos, users, favorites from the terminal 📺

KK

kotlin/kotlin-agent-skills

Developer tools

A collection of AI agent skills useful for projects using the Kotlin language. Skills are following the Agent Skills standard, see agentskills.io for more information.

DT

deusyu/translate-book

Developer tools

An agent skill for Codex, Claude Code, and OpenClaw that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents.

RA

rorkai/app-store-connect-cli-skills

Developer tools

A collection of Agent Skills for shipping with the asc cli (asc). These skills help agents run builds, TestFlight, metadata, submissions, signing, and Apple Ads workflows.

CP

cuga-project/cuga-agent

Developer tools

Building a domain-specific enterprise agent from scratch is complex and requires significant effort: agent and tool orchestration, planning logic, safety and alignment policies, evaluation for...

EB

eatmoreduck/boss-zhipin-scraper

Developer tools

一个轻量的 ：通过 Chrome DevTools Protocol 连接本地已登录的 Chrome，复用真实登录态调用 zhipin.com 搜索 API，绕过前端字体反爬，输出含**的职位数据（JSON / CSV），并生成薪资分布、技能词频和求职材料优化提示词。同时作为 Hermes Agent Skill 提供。

LA

langchain-ai/langchain-skills

Developer tools

— This project is in early development. APIs and skill content may change.

DS

dpearson2699/swift-ios-skills

Developer tools

86 agent skills optimized for development with Swift 6.3 and modern Apple frameworks. All code examples, patterns, and guidance target the latest APIs -- Liquid Glass, approachable concurrency,...

AS

adithya-s-k/manim_skill

Developer tools

Add both Manim skills to your AI agent instantly:

UL

unclecheng-li/ai_animation

Developer tools

本仓库是基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的**。每个 Skill 是一个自包含文件夹，包含 SKILL.md（Agent 执行指令）、README.md（人类文档）、references/（Prompt 参考）和 assets/（模板 HTML）。

MS

modiqo/skillspec

Developer tools

You wrote a good SKILL.md. But did the agent actually follow it, or skip the late safety rule, grab an undeclared tool, and report "done" with no proof?