Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Add vision to text-only models in Opencode (, ) — , no manual file saving.
Open-source, local-first memory and context for AI agents. One memory store, every agent.
Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.
Self-hosted, agent-native web app and MCP server for your Obsidian-style Markdown vault. Browse, search, and edit notes from a fast UI or from AI agents.
个人知识库 MCP 服务器 — 对本地文档建立索引，并提供一组飞书 API 工具，通过 MCP 协议供 AI 客户端访问。
LogLead performs log loading, log enhancement, log feature engineering, log analysis, log anomaly detection also via MCP-server.
Agent Skills
Publish Markdown articles to X (Twitter) Articles with one command. Say goodbye to tedious rich text editing.
VulnHunter is an open-source, that applies proactive, attacker-first analysis directly to source code.
Professional white-box code security audit skill with 55+ vulnerability types, dual-track audit model, and multi-agent deep analysis.
A self-evolving AI research colleague for scientists.
Ported from the TypeScript reference implementation and extended with a Python-native runtime
An open-source AI assistant framework like openclaw
公众号/小红书封面提示词生成 skill：3:4 竖版、10 种构图风格、三轮提问、真人出镜人脸一致性
A Claude skill for slides that don't look like AI made them. Brand DNA × 20 codified design principles.
A continuously updated collection of papers on agentic SE
1. ：资料分析分值密度最高，必须先做且做对 2. ：性价比最低，留5-8分钟挑5-7道会做的，其余统一蒙 3. ：会就选，不会就蒙，单题不超过30秒 4. ：做完资料涂一次，做完言语判断涂一次，避免最后来不及
claude-red is a curated library of offensive security skills for the Claude Skills system. Each skill is a structured SKILL.
Notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.