Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
— 优先支持静态分析、dry-run 与本地靶场。exploit、横向移动、持久化、C2、数据外传等高风险能力属于受限实验特性；policy 与 sandbox 元数据不等同于操作系统或容器级隔离。
传说，在每一行代码的阴影里，蛰伏着一头来自深渊的**。它以**为食，以**为巢。无人得见其形，只因它的**。它不追逐光，不咆哮于风，只等**。当**，幽狼便**——那时，，仿佛整个世界都不曾察觉。唯有虚空记得：
a coding Agent, rpc plugin, sub-agents, hashline edits, and mcp
Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.
这是基于 everything-claude-code 进行二次开发，提供npm一键安装方式，协议沿用MIT
MoLing is a computer-use and browser-use MCP Server that implements system interaction through operating system APIs, enabling file system operations such as reading, writing, merging, statistics,...
MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows
Turn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen
Point at any GraphQL or REST API. Ask questions in natural language. The agent fetches data, stores it in DuckDB, and runs SQL post-processing. Rankings, filters, and joins over returned data work .
A simulated Claude Code project you can click through. Every file and folder in the sidebar is a real Claude Code concept — the same .
MCP server that implements Claude Code's agent teams protocol for any MCP client.
iida-mcp 是一个 IDA Pro 插件，通过本地 HTTP MCP 服务暴露当前 IDB 的静态分析能力。
Agent Skills
普通润色工具帮你改句子，：对象是否明确，工况是否成立，baseline 是否公平，实验是否真的支撑 claim，图表双栏缩放后是否还能读，返修回复是否有证据。
An agent skill that applies — Pillar Security's Secure AI Lifecycle framework — to real systems. It bundles the full SAIL V2 risk catalog (, each with mitigations and standards mappings) as reference...
Reverse-engineer design tokens (colors, typography, spacing, border radius, shadows) from any public website and generate starter JSON and CSS custom properties for your local project.
Open-source MapLibre stack for China historical maps and short-form video (HyperFrames or any MapLibre host).
▶️ Watch: Latest Update Demo | Original Overview
给 Codex 使用的开源口播视频成片导师工作流：原片可以先走可选粗剪，也可以从现成粗剪或字幕轴开始，再完成素材插入、风格选择、可选 ShotCraft 镜头参考、HyperFrames + GSAP 预览和最终成片。
A for OpenCode that brings eval-driven development to AI agent skills — based on Anthropic's official skill-creator for Claude Code, ported to TypeScript and adapted for OpenCode's plugin...
从赛题到终稿，一站式交付。双模式运行、六维选题评估、模型依赖 DAG、五人评审团、学术诚信门控、公式自动渲染——把数学建模竞赛变成可追溯、可审计的工程流水线。
This project is under active development and heavily generated by LLMs without strict proofreading. Use with caution and verify all code before production use.
If this project helps you, you can support it here or simply ⭐ the repo.
Reusable skills for Claude Code, Codex, Cursor, and similar agent environments.
A comprehensive Claude Code skill for managing Linear issues, projects, and teams. Provides patterns for MCP tools, SDK automation, and GraphQL API access.