Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCP server for querying package ecosystem data from ecosyste.ms.
Website · Docs · Dashboard · Changelog · X · LinkedIn
MCP Server to make line-based edits to a file.
DepsHub MCP Server for Effortless Dependency Updates
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.
MCP server for Google search and page fetching using headless Chromium
The provides a comprehensive framework for AI-powered command execution, plugin-based tools, and advanced features including synchronous script execution, secure Python evaluation, and knowledge...
A takeoff is the act of measuring quantities off a construction drawing. OpenTakeoff does it two ways over one engine: for an agent, and a browser canvas for a person.
MCP server that gives AI assistants deep knowledge of EV charging protocols. Add it to Claude and ask anything about OCPP 1.6, OCPP 2.0.1, Plug & Charge, smart charging, and related standards.
basemind turns any repo into an always-current map of its code, documents, history, and memory — so agents answer from instead of burning their context window on grep and file reads — and gives a...
Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android.
Agent Skills
The script. The prompt. The hosts' roles. Their voices. The content they discuss. All of it.
一个适用于 Claude Code / Codex 的技能，用来生成惊艳、带动画、单文件的 HTML 演示文稿，并内置浏览器编辑器：可拖拽对象、调整大小、编辑文本、重排页面、本地保存，并导出干净的独立 HTML。
新论文层出不穷，英文读得再顺也不如母语省心；我们想把这些论文变成排版规范、读着顺口的中文 PDF。
Drag-and-drop email editor for modern apps — source-available, MIT after two years
Swift Testing Agent Skill for AI Coding Assistants
Install and use the measurable adversarial code-audit skill with scan-only defaults and explicit permission before source edits.
从初稿搭建 · 结构修订 · 图文对齐 · 引用核验 · 投稿前预检 到 返修回复的全链路 journal-first · claim-driven · 证据边界优先
A compact agent skill for turning short prompts into beautiful, realistic GPT Image 2 images.
Direct complete videos—from the first idea to production-ready media.
Everything distilled from — a public X trader and AI/semiconductor supply-chain analyst known for tracing hyperscaler capex into upstream bottlenecks.
A production-ready OpenClaw plugin that implements the A2A (Agent-to-Agent) v0.3.0 protocol, enabling OpenClaw agents to discover and communicate with each other across servers — with zero-config...
SkVM is a compilation and runtime system that makes LLM agent skills portable across heterogeneous models and harnesses. It has four major parts: