Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A focused, type-safe that lets Claude Code (or any MCP-compatible client) drive a locally-running application — read chart state, change symbols and timeframes, fetch OHLCV bars, capture screenshots.
mcp-repl is an MCP server that gives an agent a persistent Python or R session, kept alive across tool calls.
Welcome to the Twitter MCP (Multi-Channel Platform) Server! This application helps you manage your Twitter account programmatically with a variety of powerful features.
TypeScript toolkit for the Plaud API: core library, CLI, and MCP server with automatic token management.
An MCP server that allows you to run Node.js scripts and npm commands, with permission prompts via node-notifier.
Illustrative estimates. The ~90% is Claude-side token reduction on analysis-heavy tasks — not total cost: Kimi's own subscription still applies.
Keyboard-first local Markdown notes with Vim motions, diagrams, and MCP integration.
Navigate every data source — native speed, agent-ready, zero Electron bloat.
Local-first web intelligence for AI agents —
Coding assistant MCP for Claude Desktop
Native macOS App Store Connect tool with MCP. Submit iOS apps to App Store with AI agents
Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.
Agent Skills
Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
A skill bundle in Claude Code Skills format. It covers the 100 most-used Bioconductor packages the top 100 rising-star packages (newly released since ~2021 and fast-growing) from the BioMate-KB...
Write a SKILL.md, drop in some evals, and find out — empirically — whether your skill actually makes the model better at the task.
Vibe-coded products are ugly in the same specific way: indigo gradients, glowing cards, emoji everywhere, a mascot in every corner, ALL-CAPS stat-cards.
Thirteen curated Agent Skills package the steps, templates, scripts, examples, and quality gates behind repeatable work. They follow the open SKILL.
The easiest way to evaluate your Agent Skills. Tests that AI agents correctly discover and use your skills.
Demo: Analyzing 2 years of NVDA, AMD & SPY stock data (15,000+ lines of raw JSON) using DeepSeek V3.2
A source-available Codex skill for distilling photographs into sparse editorial abstractions.
这里不是一叠孤立的提示词。每个 Skill 都用 SKILL.md 固化触发条件、工作阶段、确认门槛和交付物，让 Codex、Claude Code 等 Agent 在产品、开发、研究、写作和日常效率任务中按同一套方法工作。
A curated marketplace of Claude Code plugins for software engineering workflows.
One command. 25 agent skills. Zero to profitable business.
- 🤷 "AI到底能帮我做什么？" —— 听了100场演讲，还是一头雾水 - 💸 "我该先投哪个方向？" —— 怕投错钱，更怕错过窗口期 - 📊 "别人都在用AI了？" —— 焦虑但不知道从哪开始