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
Server implementation of the Model Context Protocol (MCP). Currently allows tools to be exposed to LLMs supporting the protocol.
Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's...
MCPC is the SDK for building agentic MCP (Model Context Protocol) Servers. You can use it to:
A Model Context Protocol (MCP) server implementation for the Gmail API, providing a standardized interface for email management, sending, and retrieval.
DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.
A powerful LinkedIn profile analyzer MCP (Model Context Protocol) server that interacts with LinkedIn's API to fetch, analyze, and manage LinkedIn posts data.
Convert any MCP server into a Claude Skill with 90% context savings.
Ultra-fast semantic tool filtering for MCP (Model Context Protocol) servers using embedding similarity. Reduce your tool context from 1000+ tools down to the most relevant 10-20 tools in under 10ms.
is now fully supported and can be used directly from GASADK (Google Apps Script Agent Development Kit).
A Unified MCP Server Management App (MCP Manager).
A Model Context Protocol (MCP) server that provides access to WolframAlpha's LLM API. https://products.wolframalpha.com/llm-api/documentation
Manage Tampermonkey userscripts via Model Context Protocol (MCP). List, read, write, patch, and delete userscripts directly from AI-powered development tools.
Agent Skills
—— 凌驾于全部技能/工具之上的元规则，强制 Agent 先查后用、有匹配必用、无匹配必搜。跨平台通用（WorkBuddy / Claude / ChatGPT / Cursor / Gemini / ...）
Make AI understand your Xiaohongshu (RedNote)
Aeloon is a lightweight, high-performance, and modular AI agent framework featuring graph-driven parallel acceleration and flexible hot-swappable plugins for many usages (Deep research, Wiki,...
VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill.
This skill makes an AI agent run error analysis on a dataset. Point it at a JSONL/CSV/JSON file of LLM outputs or traces, and it:
Persistent memory for AI coding agents. Your agent remembers what it learned across sessions.
A hands-on showcase for anyone running Agentic Coding Agents at scale on macOS.
把已经导出的 MP4、MOV 交给 Agent，依次完成转录、术语纠错、人工预览、章节生成和 FFmpeg 烧录。默认只生成中文字幕，只需要一个百炼 API Key。
Letta-like memory management for pi using git-backed markdown files.
Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.
面向 CS 顶会论文写作的 7-Agent Pipeline Skill，运行在 Claude Code 之上。将一个粗糙的研究想法变成一篇投稿就绪的顶会论文，覆盖从选题到 Rebuttal 的完整管线。
Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.