Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp
Find risky code, AI-agent vulnerabilities, and supply-chain issues before they ship. Website · Docs · Security & Data Flow · Benchmark · Pricing · Blog
NEW · Agent in the loop — Using AI to assess the risk of one-off operations. Read more → One Gateway Between Your Team and Your Infrastructure. hoop.
Agentic Capabilities and Package Manager
Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles,...
Real websites for your coding agent to learn design from, searchable over MCP.
Buoy is a floating dev menu that ships inside your React Native app — every request, state change, render, and frame, live on the phone, on your desktop, and in Claude or Cursor.
All in one vscode plugin for mcp developer
adb-mcp is a proof of concept project to enabled AI control of Adobe tools (Adobe Photoshop and Adobe Premiere) by providing an interface to LLMs via the MCP protocol.
Diagram generation for understanding codebases and system architecture using Nano Banana Pro.
MCP configuration to connect AI agent to a Linux machine.
Cross-session context persistence for AI coding. A file convention, a CLI, an MCP server, and Claude Code/Codex skills that together turn every coding session into a building block instead of a reset.
Agent Skills
一个 Claude Code , 可直接使用的科研写作指导,覆盖写作、修改、评审与报告——。
A repository template for with Claude Code that organizes the entire software development lifecycle (SDLC) into four phases — Specification, Design, Code, Deploy — each with folder structure,...
Claude Code version of skill-autoimprove — auto-improve any CLAUDE.md using Karpathy autoresearch loop
一个适配 Claude Code / Codex 等 Agent 的桌面副屏 Skill。把 M5Paper V1.1 4.7 寸墨水屏立在显示器旁边，由 AI Agent 推送 widget：天气、日程、todo、PR 队列、AI 状态、休息提醒……
VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill.
Claude Code skill to extract React components from any production website
An AI-powered workflow that searches London rental platforms twice a day, tracks listings in a spreadsheet, generates personalised outreach messages, and emails you a formatted summary — fully...
Claude Code skill for multi-reviewer peer review of academic papers. Adapted from poldrack/ai-peer-review — uses parallel Claude subagents instead of multiple proprietary LLMs.
面向 CS 顶会论文写作的 7-Agent Pipeline Skill，运行在 Claude Code 之上。将一个粗糙的研究想法变成一篇投稿就绪的顶会论文，覆盖从选题到 Rebuttal 的完整管线。
A set of Claude Code skills and hooks I use daily as scaffolding for staying organized while developing with AI agents.
This project is a practical manual and starter kit for running a complete workflow with AI, from product requirements and implementation planning to coding, verification, and code review.
A prompt framework for Claude Code that enforces strict TDD, Clean Architecture, and DDD across the full stack.