Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

Generative UI examples for: AG-UI, A2UI/Open-JSON-UI, and MCP Apps.

❤️ Generate mermaid diagram and chart with AI MCP dynamically.

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

Runno is a collection of JavaScript Packages for running code in various languages inside a sandbox. It's made of the following packages:

An MCP server for interacting with Google Colab

Shell and coding agent on mcp clients

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools.

"You never truly know the value of a moment until it becomes a memory."

AST-based call graph analysis + semantic search — right from your terminal.

An open-source, bilingual, AI-native Web3 curriculum for beginners, builders, and agents. 11 modules, 62 lessons, AI Tutor, badges, SEO prerendering, llms.txt, and a read-only MCP server.

An MCP service for deploying full-stack projects to EdgeOne Makers and obtaining publicly accessible URLs.

这是一款基于 Playwright 开发的小红书自动搜索和评论工具,作为 MCP Server,可通过特定配置接入 MCP Client(如Claude for Desktop),帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。
Agent Skills

基于中国大陆法律体系 | 成文法方法论 | 请求权基础分析法 | 三阶段自动化工作流程

Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升,一个现实需求也逐渐显现:面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程,希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。

Ask Why - BA Elicitation Skill by BA Zone

A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...

A Claude Code plugin that conducts deep behavioral interviews, reads work artifacts via MCP tools, and generates installable plugins that authentically embody a person's thinking, communication, and...

For engineers who want agents shipping code without a human in the loop.

Google Docs for markdown files — real-time multiplayer editing, comments, suggestion mode, edit history, and a CLI built for AI agents.

微信读书前几天上了一个官方 AI skill(weread.qq.com/r/weread-skills),把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强,但它只是「自然语言包装的搜索接口」——你让它推荐书,它不会去看你已经读过什么,常把你笔记 68 条的书又当新书推回来给你。

基于 Claude Code 官方 skill-creator,我融入了自己对提示词架构、Skill 架构以及 CLI 工具运行机制的理解,对其进行了全面重构,打造了一个新版 Skill Creator。 在测评环节,我采用 Codex 的 Headless 模式(无需打开图形界面,直接在终端执行)进行了三轮以上的独立对话测试。测试结果显示,新版在各项维度上全面超越原版。

Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...

JourniOne 旅行规划 Skill:从灵感与逐日路线,到带地图、可分享的 Travel Journal,按需衔接酒店与航班。

出行路书工作流 skill:联网实查 + 多源交叉验证,产出可核验、能执行的旅行攻略。覆盖吃住行游拍避全维度,附美食情报卡、基准骨架与校验工具,支持一键部署在线版。