Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Buy me a coffee on Patreon if this project helps you. I am not very familiar with editing Patreon pages yet; thanks for your understanding.
豆包搜索是火山引擎为 AI Agent 构建的联网信息服务，2026 年 7 月起面向企业和开发者开放。
A collection of 8 Claude Code skills + an implementing a : an AI-powered conversational workflow for C2C second-hand resale that reduces the barriers to listing and selling pre-owned goods.
A macOS desktop app that captures screenshots, windows and apps (both background and foreground) on a schedule and transforms them into a timeline, daily summaries, project milestones, and addiction...
Photon is the fastest way to turn a small, verified TypeScript method into something humans can operate and agents can trust.
A type-safe, declarative framework for building AI agents in Swift, built on Apple FoundationModels.
CLI for Tana integration - query, create, sync, and manage Tana workspaces with semantic search and MCP Server
MCP server for automated "talking head" video editing. Reads CapCut's auto-generated subtitles to find and remove silences and duplicate takes — directly in the CapCut project.
An MCP server application that sends various types of messages to the WeCom group robot.
An MCP server that exposes UniFi application API documentation (Network, Protect, Site Manager) as queryable tools for Claude Desktop, Claude Code (VS Code / JetBrains), or any MCP-compatible client.
The plugin integrates the into FreeCAD, enabling automation of model creation, macro execution, and view management through a server-client architecture.
Pare provides MCP servers that wrap common developer tools (git, npm, docker, test runners, etc.) and return clean, schema-validated JSON instead of raw terminal text.
Agent Skills
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).
开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversarial review.
Agent Skill: make Claude write in Barbara Minto's Pyramid Principle - answer first, grouped reasons, evidence under each.
The official WordPress AI benchmark. Evaluate how well language models understand WordPress development—from core APIs and coding standards to plugin architecture and security best practices.
Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources
这里收集的是泊舟日常做 AI / 科技自媒体时常用的 Agent Skills，覆盖 AI 资讯、选题、推文、长文、标题、去 AI 味、配图、公众号发布和 X 发布等工作流。
A small collection of Codex skills for goals, planning, execution, and code understanding.
A framework-agnostic, git-native standard for defining AI agents
科研写作助手 (Research Writing Assistant)
Pi extension for async subagent delegation with truncation, artifacts, and session sharing
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge...
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.