Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
AI agents create, edit, layer, animate, and export SVG files using Inkscape. Works as an MCP server (stdio/HTTP), Claude Desktop .mcpb bundle, webapp dashboard, or Windows desktop app.
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
Find local coding-agent sessions and copy their user and assistant messages into another agent's native format. TUI, CLI and MCP.
28 plugins and MCP servers for Claude Code — parallel exploration, iterative refinement, binary reverse engineering, structured decision-making, and more.
Tell your AI to demo your app. Pagecast records the browser, tracks every click and keystroke, and exports a shipping-ready GIF or MP4 — with tooltip zoom overlays and cinematic pan effects.
An MCP server for exploring Israeli government open data (data.gov.il) — with built-in interactive visualizations powered by MCP Apps.
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway.
Open-source, local-first memory and context for AI agents. One memory store, every agent.
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
Claude Code rewritten in Go.. High-performance AI agent harness runtime in Go. MCP server, CLI tool orchestration, session management, Kiro integration. Single binary, zero dependencies.
Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation
Agent Skills
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects.
50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
A skill is a folder containing a SKILL.md file with instructions an agent loads on demand. Think of it as a reusable, portable prompt: when this scenario comes up, do these things.
A set of ready to use Agent Skills for building, testing, analyzing and publishing browser extensions.
Directly edit and manage Overleaf projects from Codex or a terminal. The bundled enhanced olcli sends small, verified remote changes instead of requiring a download-edit-upload cycle for the whole...
开源我自己做的一下好用的skills
An Extensible Agentic Markup Language
Claude Code skill for academic manuscript writing: IMRAD workflows, literature matrices, tables/figures, and tested utilities.
20亿Claude Opus 4.6-4.8的Token
面向全国大学生数学建模竞赛（CUMCM）的完整建模论文分步审核工作流技能，兼容 Codex、Claude Code 等支持 Agent Skills 规范的 Agent。
它扣掉的只有两件事：固定 IP 形象和固定配色。使用者只需要填写自己的 IP 角色公式和品牌配色，就可以把文章、知识点、教程内容转成一套带个人风格的配图 Prompt。
SEO Landing: Give your AI coding agent the capabilities of a senior Technical SEO engineer. An agent skill for building high-performance, technically optimized SEO landing pages.