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

Open-source AI podcast clipper. Turn a long episode into short clips with face tracking and burned-in captions. Drive it from the CLI, a web studio, or your coding agent.

Local-first creative studio with 37 model routes, transparent costs, local archives, and MCP access.

28 plugins and MCP servers for Claude Code — parallel exploration, iterative refinement, binary reverse engineering, structured decision-making, and more.

Run it before Claude Code, Cursor, Windsurf, Cline, OpenCode, or another agent trusts new code, tools, prompts, or dependencies.

Tool names match exactly what each server exposes. Tool-call output passes through unchanged (text or JSON), so you can pipe, redirect, or parse with jq.

⚠️ :此项目完全是 vibe coding 产物,代码由 AI 生成,未经严格审查。使用风险自己承担。

Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

The local-first knowledge layer for AI development.

MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in

This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).

One command. TypeScript Python. Example tools, the Inspector, and tests — all wired up. Or point it at an OpenAPI spec and get

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

MIT licensed · Works with Claude Code & Codex · Pure Markdown + two small Python scripts, no dependencies

(formerly "AI Shortcuts") is a browser extension that lets you compare answers from multiple AI models in one place.

A practical configuration kit for Claude Code, Codex, and other coding agents. It contains architectural principles, enforcement hooks, skills, drop-in rules, starter templates, and dynamic-workflow...

Web 界面的源码、构建脚本、core/registry 实现与 Rust CLI 都在私有仓 HaddenHunter/SkillForge-Core。本仓 main 分支**(技能清单、文档、镜像配置等);可访问的静态站点由 Core 仓的 Actions 构建后,跨仓推送到本仓的 gh-pages 分支,由 GitHub Pages 服务。

recursive-mode is an installable skill package for structured AI-assisted software development.

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

Run one command → open the dashboard → your bot is live. Windows · macOS · Linux · VPS — Docker-powered, auto-installed for you.

AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — from Claude Code or GitHub Copilot.

Production-ready Claude Code skills, agents, and project templates for Craft CMS 5 development

一个用于存放可复用 Claude Skills 的仓库。每个 skill 都是独立目录,入口文件为 SKILL.md,可按场景直接复用或继续扩展。

https://github.com/user-attachments/assets/8bc180a3-0baf-473d-87c9-6aaacce302f2

GLM-OCR: Accurate × Fast × Comprehensive