Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Persistent memory and codebase intelligence for AI coding agents, indexes symbols, tracks sessions, and exposes structured project knowledge through an MCP server so agents stop re-reading files and...
Skarn plugins for Claude Code, Codex CLI, Gemini CLI, Grok Build, and Antigravity: audit skills, guard hooks, and MCP declarations that find leaked secrets and credentials in AI coding sessions,...
Local-first AI canvas and timeline. Any MCP agent. Open-source alternative to Higgsfield.
Self-hosted MCP server for docs, code search, and conversational sources
Your AI conversation history, queryable from any MCP-aware LLM, stored entirely on your machine.
The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.
MCP server that gives AI coding agents semantic understanding of any codebase. Search by intent, auto-sync on edits, whole-repo context in one call. Rust + tree-sitter, 15 languages, 28 tools.
Email for AI agents — read, search, send and triage Gmail / QQ / 163 / any IMAP from the CLI or MCP. Part of the *-use family.
n2-QLN: Intelligent Tool Router & Semantic Search Layer for MCP. Connect 1,000+ tools through 1 interface. Prevent AI model confusion and maximize context window efficiency
The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.
Universal installer and configuration guide for NotebookLM MCP server.
Serve any AI a Malloy semantic model over MCP — accurate, consistent answers from your data.
Agent Skills
Podcast to Course 专治这种「听过 ≈ 学会」的错觉：它把播客变成**，让洞见不再从左耳朵进、右耳朵拿着离职证明出去。
An open agentic prompt-expansion harness for image and video generation. Turn everyday intent into validated, model-ready prompts through a bounded AI-agent workflow.
把 Taiji / TAAC 训练与评估平台变成任何人和任何 agent 都能读取、比较、归档、提交训练、发布模型和收集线上评估证据的实验命令行工具。
Turn a web page into records your agent can use, from one 3 MB binary.
Tailwind CSS v4 plugin for smooth easing gradients
Step-by-step causal inference — method selection, assumptions, and robustness checks
This is the branch tracking v7 work. If you are looking for the published latest on npm check out v6 branch.
*Write projections easily with generation*.
本项目的角色卡编写方法论和提示词设计大量参考了 sanmingyue 大佬的写卡教程与工作流理念，是本技能写作规范的基石。
wecom-codex-bridge
civ-finish-quotes is a platform-neutral skill and toolkit for adding Civilization-style completion quotes to real finished work.
DSH 生态增长极快，插件与技能散落在 GitHub 各处 —— 。DSH Market 用一个平台收齐它们，并提供两种消费入口：