Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
comprehensive Discord selfbot MCP server using discord.py-self
A minimal MCP server built on crawl4ai for LLM-friendly web extraction
3 collaboration commands for Claude Code that use the Codex MCP server to generate parallel plans, validate plans, and brainstorm ideas.
is a battery-included implementation of the framework with support for the multi-agent architecture. Ship autonomous agents that can reason, write, execute & iterate over code.
CROW - Your AI Agent. MCPs, OpenRouter, Any Model or local. It's your choice.
An MCP server that connects Claude Code to Perplexity Comet - enabling agentic web browsing, deep research, and real-time task monitoring.
An MCP server implementation for configuring OpenTelemetry Collectors.
AI-powered browser automation for Claude Code by DebugBase
A local-first MCP server that gives AI agents shared, durable memory through hybrid semantic search, SQLite FTS5, and a knowledge graph—without Docker or a required cloud service.
Prompt-based frameworks hope the LLM follows instructions. This one blocks the call if it doesn't.
An MCP server that provides access to Facebook Marketplace via direct GraphQL API calls. No browser automation at runtime — speaks Facebook's internal protocol directly.
Learn how to Power BI semantic model tasks - documentation, naming audits, and more - to GitHub Copilot coding agent, powered by the Power BI Modeling MCP Server.
Agent Skills
Give this GitHub link to Codex or Claude Code to create presentations
This is a repository of prompts, instructions, and skills I often use with AI coding agents.
OpenCode port of academic-research-skills: 4 skills, 13 slash commands, 38-agent pipeline for academic research, writing, peer review, and revision
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。
A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.
Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mistakes. A manual Reflexion loop, built on the US Army's AAR method.
A synthesis of Claude Code best practices, aggregated from Twitter.
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
A portable framework that reduces the cognitive load of working with AI coding agents — plan, build, verify, milestone by milestone.
Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.
AI 做 PPT 最常见的失败，是交付一堆静态文字页。这个 skill 把资料变成可编辑、可演示、可离线分发的单文件 bento deck。 Turn source material into an editable, presentable, offline-ready bento deck — one self-contained HTML file.
This is the official website for TuriX Computer-use-Agent