Claude Desktop Install Guide
Desktop client with local MCP configuration support.
MCP Servers
One command. TypeScript Python. Example tools, the Inspector, and tests — all wired up. Or point it at an OpenAPI spec and get
Your digital developer twin — because "explain our setup again" gets old fast.
The local-first knowledge layer for AI development.
Agent Skills
A multi-role AI design team skill for research, planning, scripting, design, and content production. 由設計實驗室 @pb_design_lab 專為內容創作者打造的 Claude AI 虛擬團隊，10 個專業角色分工協作，涵蓋從業配分析、內容企劃、腳本撰寫到社群發布的完整製作流程。
Connect your Claude agent to Google NotebookLM. Add sources automatically, query your notebooks, generate branded slide decks, and keep your auth alive without manual re-login.
A library of (SKILL.md + optional references/) covering 3 kinds (persona / tool / workflow) across 60+ domains.
A production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system, not as isolated features.
A shadcn-style registry of agent UI primitives — message lists, streaming markdown, tool cards (Bash, Edit, Search, Todo, Plan…
A framework-agnostic skill system for AI agents that implements - a powerful pattern for managing context efficiently.
AI Frontend Guard 是一个专为前端开发者设计的AI代码质量管控工具。当使用 Claude Code、GitHub Copilot、Cursor 等AI编程助手时，它能帮助你：
Make Claude Opus, Sonnet, GPT, or Gemini produce work close to what Claude Fable 5 would ship. 21 craft standards written and audited by the frontier model itself; single-response lift, or a full...
1688 商品全方位分析诊断工具，整合多个数据源对指定商品进行深度分析。当用户需要分析某个指定商品表现、诊断流量问题、优化商品策略时使用。适用于指定商品的：商品数据分析、销售表现诊断、搜索排名问题分析、广告效果评估、市场竞争分析、商品优化建议。触发关键词包括"分析这个商品"、"商品诊断"、"商品表现分析"、"为什么商品没流量"、"商品优化建议"、"商品数据分析"等。
Use the same skills and agents on your work laptop, personal machine, servers, and whichever AI tools you use. Put the setup in a repo when you want to share it with a team.
Agentic chat runtime where markdown is the protocol
**의 내부 프롬프트 아키텍처와 에이전트 동작 방식을 문서화한 독립 연구 프로젝트입니다. Claude Code는 Anthropic의 AI 기반 소프트웨어 엔지니어링 어시스턴트입니다.