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

General-purpose MCP bridge for Ableton Live

One command. Full visibility. Read-only.

api router for MCP Servers

MCP server for searching and retrieving flight information using Duffel API.

小智AI客户端,目前主要用于MCP的对接

一个本地优先的 AI 知识库系统(RAG),用于将本地文档接入向量检索与大模型对话流程。项目提供 Web UI,支持知识库管理、文档上传、检索增强问答、聊天记录持久化,以及基于 Ollama 或 OpenAI 兼容接口的模型接入。

Control Adobe Premiere Pro through MCP using Codex, Claude Code, Claude Desktop, or any other MCP client.

System Audio Capture | 12 ASR Providers | Local-First AI Review Workspace

基于 FastAPI + LangChain + OpenAI 构建的小红书内容挖掘与自动生成系统。支持从爬取竞品数据、分析爆款规律、AI 生成文案与配图,到一键发布至小红书的完整闭环。

⚡ — Cross-session orchestration: wake system v2 (dynamic /loop, event watcher, turn-end guard) + targeted sibling-session driving + agent reuse recommendation + context watermark observability.

A working pattern for SSE-based MCP clients and servers

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool...
Agent Skills

个人开发的 Claude Code Skills 集合,提供实用的技能工具,助力提升开发效率和内容创作。

This is the v3.0 rewrite of EasyApi. For the source code of stable v2.x releases, see the stable/v2.x.x branch.

Heads up: the more agents you run, the more this skill is doing on hard mode — rebuilding context from transcripts every time.

29 interconnected skills covering building architecture from design theory through construction documentation, providing clause-level precision for India, UAE, Saudi Arabia, USA, UK, Germany,...

一个面向社会科学论文写作的 Codex / ChatGPT Skill,用于辅助完成选题诊断、研究问题细化、论文大纲搭建、文献综述规划、文献检索到 Zotero 工作流、草稿评审、章节修订、引用与证据风险检查,以及投稿前检查。

纠结跳槽还是留下,AI让你"列优缺点清单"——:反者道之动,不纠结的时候自然就清楚了。

Automatically download books from Anna's Archive and upload them to Google NotebookLM with one command.

No setup required · Works for any company or industry

Reverse-engineer any website's design taste. Tokens + trade-offs — not just "what", but "why".

A skill catalog that won't let you spend 6 months on a research gap that's already closed, isn't a real contribution, or isn't feasible.

https://github.com/user-attachments/assets/831e8453-d3fa-41ad-99f6-39b13ce498d0

Fable5 구조를 넣은 Sonnet이 Opus와 블라인드 테스트에서 사실상 비겼다!! 그것도 답 1건당 비용 3분의 1로!! Sonnet + Fable 5 structure virtually tied Opus in a blind test — at 1/3 the cost per response. (bench/)