Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Claude Code memory that learns from corrections. The only MCP server that measures whether your agent actually stops repeating a mistake.
An Obsidian-native memory layer for your AI agent. Plain Markdown you own, in the same vault you already use.
An MCP server that provides access to arXiv papers through their API.
An MCP server to use with AI agents such as OpenCode, Mai, VSCode, Claude, CLION, ...
Watch Skill turns videos, live streams, meetings, and screen recordings into a searchable, timestamped index.
A Nix-based configuration framework for Model Control Protocol (MCP) servers with ready-to-use packages.
本仓库的公开 Git 历史已于 2026-04-21 重新整理。如果你在该日期之前克隆过本仓库，请在继续贡献前重新克隆。不要从旧的本地克隆直接合并或推送，否则可能会把过期历史重新引入仓库。
If you find this repo useful, please also star our ⭐
llamacloud-mcp is a tool that allows you to use LlamaCloud as an MCP server. It can be used to query LlamaCloud indexes and extract data from files.
Some users may see already installed with an old version when running brew upgrade claude-in-mobile. This happens when the local tap points to the wrong repository. Fix:
It is the navigation manifest for this codebase — where to find every module, how they connect, and where to look before making any claim about the code.
OpenMCP makes it easy to turn any OpenAPI specification into an MCP server, and to remix many MCP servers into a single server with just the tools you need.
Agent Skills
🔴 RedTeam Agent Autonomous AI-Powered Red Team Simulation Agent Install · Quick Start · Architecture · 中文
Cost-efficient Codex multi-agent orchestration using Sol for planning and review, Luna for implementation, and Terra as a fallback.
ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth before coding.
Most popular OSS agent harnesses (Cline, Roo Code, Continue, OpenCode, Aider) leave on the table because their prompt-caching code is subtly wrong, off-by-default, or just missing for some providers.
Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mistakes. A manual Reflexion loop, built on the US Army's AAR method.
给 AI 编码助手用的「工作台架构师」技能。它不写界面 —— 它负责回答*这东西到底是什么*，然后输出一份能直接开工的 ，交给 finesse-ui 或任何会写页面的 AI。
A catalogue of — CRUD tables, detail & master-detail pages, kanban, calendar, wizard, charts, billing, RBAC, i18n, and more — that an AI agent into a real back-office.
Pi package with agent-first skills and prompt templates for structured codebase understanding, safe greenfield starts, safe changes, architecture-aware review, structured-doc validation, and...
Spec-driven thinking, nano-sized docs. Lightweight task specification for AI-assisted development.
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
的 AI Agent 工作台，一定程度上解决Openclaw的长期记忆及安全问题： 1. 对话与证据落盘为本地 JSON； 2. 长期记忆由 memory_module_v2 做结构化蒸馏与混合检索实现11倍tokens压缩； 3. 接入自己微调的Qwen3.5 4b模型配合Langchain的before_agent middleware用于合规内容检测； 4.
humanizer-zh 是一个兼容 Codex、Claude Code 和 OpenClaw 的中文去 AI 味技能。它用于重写、润色或审阅中文博客、评论、产品分析、newsletter、书稿章节等长文本，让文字更像中文母语者写出来的，而不是翻译腔、模型拼接稿或营销通稿。