Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human

MCP server to enable an LLM to do basic static triage of a PE.

Intercept AI requests, track usage, inject MCP tools centrally

🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama

is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.
Agent Skills

Open agent skills for Alpaca's Trading API and Broker API. Each skill is a SKILL.md file with step-by-step instructions your AI coding assistant follows when you ask it to complete a task, such as...

Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca...

Claude Code skill/plugin: Remnawave + Xray Reality/Vision + Caddy selfsteal + mihomo — reference, config generation, diagnostics

provide for AI agents, helping them build complete automated document workflows. Before large-model reasoning begins, ComPDF Skills can handle document parsing, OCR, data extraction, and structured...

AI agents should not give project advice from vibes.

Comprehensive best practices for building applications with the TanStack ecosystem. These skills provide AI coding agents with structured guidelines for TanStack Query, TanStack Router, and TanStack...

Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.

A curated list of high-signal resources for (formerly , originally ): frameworks, skills, tooling, deployments, and real-world use cases.

🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.

A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.