Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCP server for Exa Search API.
The only Apple Mail MCP server with — reliable on large mailboxes where AppleScript-based servers timeout. 8 tools for reading, searching, and extracting email content.
A TypeScript-based MCP server that enables testing of REST APIs through Claude, Cline and other MCP clients.
A Model-Context-Protocol server for interacting with multiple blockchains including Solana, Ethereum, THORChain, XRP Ledger, TON (The Open Network), Cardano, and UTXO chains.
Official Mobbin MCP server repository
Claude Code skills that let Claude interact with Web of Science (WoS) through Chrome DevTools MCP.
"It's like Gmail for your coding agents!"
AgentMail has one MCP tool implementation, hosted at:
Arm's MCP server
ACI indexes your code with embeddings and Tree-sitter AST parsing, then lets you search it with natural language. Results come back with exact file paths and line numbers, not just fuzzy matches.
一个用于连接 和 的本地桥接项目。它通过文件队列 IPC 让外部 AI 助手向 Workbench 或 ICEM CFD 发送命令，并在 Ansys 进程内执行脚本和返回结果。
Offensive security you run yourself — a local MCP workflow for authorized testing, in CI or against staging.
Agent Skills
We are moving from "prompt as text" to . Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be...
A behavioral governance framework for GitHub Copilot agents — skills.md and instructions to make AI coding agents think like senior engineers.
漫画风格图解生成器 Skill | 10+ 动漫风格（哆啦A梦/火影/海贼王/龙珠）| 兼容 Cursor / Claude Code / OpenClaw | 附图解 OpenClaw 示例漫画
Security skills for AI coding assistants and agentic systems
If you'd like to support these efforts consider becoming a paying Patreon member ❤️ You'll even get access to up to date lessons and other perks: patreon.com/TheHotwireClub
Official Sketch Plugin directory
Process skills that give a Reasonix coding agent the disciplines of a careful engineer: write the test first, debug from evidence, plan before coding, verify before claiming done.
*Tuned for (1M-token MSA context, native multimodal input) and (Agents Window, canvases, Design Mode, /worktree, /best-of-n, Await, MCP Apps). Written to stay useful across model changes.*
"一器而工聚焉者，车为多。" ——《考工记》 两千年前，造一辆马车是最复杂的系统工程：**承载乘者，辕定方向，辐传动力，軎辖为约束——每个构件各司其职，合而为一，车方能行。 今天，构建一个 AI Agent 亦是如此：对话循环为**，工具系统为**，权限管线为**，而将这一切承载于其上、使智能体真正运转的运行时框架—— Agent Harness——正是那个**。
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
cv4pve-cli is to Proxmox VE what kubectl is to Kubernetes — a remote-first CLI with context switching, direct API access, and aliases for common operations.
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA