Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
Infinite text-free AI image generator + SQLite-indexed multilingual vault & gallery — with a local MCP your AI can drive.
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.
Code Mode MCP server for App Store Connect — 923 endpoints through 2 tools
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.
MCP server for Divar — search, compare and analyze classified ads. Read-only, no API key.
Access thousands of AI prompts directly in your AI coding assistant
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.
Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.
MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice
Agent Skills
—— 凌驾于全部技能/工具之上的元规则，强制 Agent 先查后用、有匹配必用、无匹配必搜。跨平台通用（WorkBuddy / Claude / ChatGPT / Cursor / Gemini / ...）
Make AI understand your Xiaohongshu (RedNote)
Aeloon is a lightweight, high-performance, and modular AI agent framework featuring graph-driven parallel acceleration and flexible hot-swappable plugins for many usages (Deep research, Wiki,...
VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill.
This skill makes an AI agent run error analysis on a dataset. Point it at a JSONL/CSV/JSON file of LLM outputs or traces, and it:
Persistent memory for AI coding agents. Your agent remembers what it learned across sessions.
A hands-on showcase for anyone running Agentic Coding Agents at scale on macOS.
把已经导出的 MP4、MOV 交给 Agent，依次完成转录、术语纠错、人工预览、章节生成和 FFmpeg 烧录。默认只生成中文字幕，只需要一个百炼 API Key。
Letta-like memory management for pi using git-backed markdown files.
Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.
面向 CS 顶会论文写作的 7-Agent Pipeline Skill，运行在 Claude Code 之上。将一个粗糙的研究想法变成一篇投稿就绪的顶会论文，覆盖从选题到 Rebuttal 的完整管线。
Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.