智能修正术 HTML编辑新篇章。

Archify 是一个面向 Cursor、Claude Code 等 AI 编码工具的 Agent Skill，能将代码库或系统描述编译成可交互的 HTML/SVG 架构图。它通过类型化 JSON IR 确保输出确定且可验证，支持 diff 对比、多格式导出和上下游追踪，让设计工程师在对话中就能完成系统文档的可视化与审阅。

K-Dense 在 GitHub 开源了 135 个 Scientific Agent Skills，覆盖癌症基因组学、分子动力学、时序预测等领域，任何支持 Open Agent Skills 标准的 AI Agent（如 Claude Code、Cursor、Codex）都可直接调用。团队还推出了免费的桌面端 AI 科研助手 K-Dense BYOK，支持 40+ 模型与 100+ 科学数据库，数据完全本地留存。

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins. Claude Code Plugins Directory A curated directory of high-quality plugins for Claude Code. ⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information. Structure /plugins - Internal plugins developed and maintained by Anthropic /external_plugins - Third-party plugins from partners and the community Installation Plugins can be installed directly from this marketplace via Claude Code's plugin system. To install, run /plugin install {plugin-name}@claude-plugins-official or browse for the plugin in /plugin > Discover Contributing Internal Plugins Internal plugins are developed by Anthropic team members. See /plugins/example-plugin for a reference implementation. External Plugins Third-party partners can submit plugins for inclusion in the marketplace. External plugins must meet quality and security standards for approval. To submit a new plugin, use the plugin directory submission form. Plugin Structure Each plugin follows a standard structure: plugin-name/ ├── .claude-plugin/ │ └── plugin.json # Plugin metadata (required) ├── .mcp.json # MCP server configuration (optional) ├── commands/ # Slash commands (optional) ├── agents/ # Agent definitions (optional) ├── skills/ # Skill definitions (optional) └── README.md # Documentation License Please see each linked plugin for the relevant LICENSE file. Documentation For more information on developing Claude Code plugins, see the official documentation.

bilawalsidhu/gods-eye-view

A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe. https://maptheworld.ai/ 🌐 God's Eye View A spy-satellite simulator in your browser — then you realize the sources are public and the data is real. Photorealistic 3D globe. Live aircraft, ships, satellites, earthquakes, traffic, and public cameras, with clearly labeled modeled views where a live feed is unavailable. Hands-free voice control powered by a realtime AI agent. No place left behind. ▶️ From the project behind the viral God's Eye View series (formerly WorldView) — 5M+ on YouTube Quick Start · First Five Minutes · Talk to It · What's Live · Under the Hood · Keys · Costs 🌍 Why This Exists You asked, so it's happening. God's Eye View is open source. Track the world live. Talk to it. Break it. Extend it. Most open-source intelligence is a pile of browser tabs. The signals are abundant, but the interface is the bottleneck. God's Eye View turns those signals into a place: the world is already broadcasting — flight transponders, ship beacons, orbital elements, seismographs, public cameras — and this makes it visible on a photorealistic 3D Earth in real time. No classified clearance required; it's public signal all the way down, and the interface runs in your browser, under your control. Half the magic is that it looks like a forbidden cockpit. The other half is that every line of code is inspectable. The live layers are grounded in public feeds: the airliner crossing your screen is reporting telemetry, the camera is installed at a published location, and the ISS position is propagated from current orbital elements. The client deliberately renders flights one polling interval behind real time so it can interpolate smoothly. Some experiences are modeled rather than live: keyless traffic is labeled as a simulation, camera poses are estimated until calibrated, and launch asc…[truncated]

abhigyanpatwari/GitNexus

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration https://gitnexus.vercel.app GitNexus (Akon Labs) ⚠️ Important Notice: GitNexus has NO official cryptocurrency, token, or coin. Any token/coin using the GitNexus name on Pump.fun or any other platform is not affiliated with, endorsed by, or created by this project or its maintainers. Do not purchase any cryptocurrency claiming association with GitNexus. The nervous system for agent context. Indexes any codebase into a knowledge graph — every dependency, call chain, cluster, and execution flow — then exposes it through smart MCP tools so AI agents never miss code. 💬 Discord · 🌐 Web UI · 🏢 Enterprise (SaaS & self-hosted) https://github.com/user-attachments/assets/172685ba-8e54-4ea7-9ad1-e31a3398da72 Like DeepWiki, but deeper. DeepWiki helps you understand code. GitNexus lets you analyze it — a knowledge graph tracks every relationship, not just descriptions. TL;DR: The CLI + MCP makes your AI agent reliable — it gives Cursor, Claude Code, Antigravity, Codex, and friends a deep architectural view of your codebase so they stop missing dependencies, breaking call chains, and shipping blind edits. Even smaller models get full architectural clarity. The Web UI is a quick way to chat with any repo in the browser. Quick Start # 1. Index your repo (run from repo root) npx gitnexus analyze # 2. Connect your editors (one-time, auto-detects Claude Code, Cursor, Codex, …) npx gitnexus setup That's it. analyze indexes the codebase, installs agent skills, registers Claude Code hooks, and creates AGENTS.md / CLAUDE.md context files — all in one command. setup writes the MCP config so your AI agent can use the gra…[truncated]

JetBrains/go-modern-guidelines

Help AI coding agents write modern Go Modern Go Guidelines This repository contains guidelines for code agents that help them write modern Go code. For example, an agent with these guidelines uses max(a, b) instead of an if-else block, slices.Contains instead of a manual loop, cmp.Or(a, b, c) instead of a chain of nil checks. It also knows about recent additions like new(42) to get a pointer to a value and errors.AsType[T](err) for type-safe error matching—both from Go 1.26. The guidelines cover the most useful features from Go 1.0 through Go 1.27, including everything targeted by the modernize analyzer. An agent will: Detect the project's Go version from go.mod Use language features and stdlib additions available up to and including that version Prefer modern idioms over older patterns Motivation All coding agents tend to generate outdated Go. Two reasons: Training data lag. Models don't know about features added after their training cutoff. They can't use errors.AsType[T] (Go 1.26) if they've never seen it. Frequency bias. Even for features the model knows, it often picks older patterns. There's more for i := 0; i < n; i++ in the training data than for i := range n, so that's what comes out. These guidelines fix both problems by giving the agent an explicit reference. This aligns with the Go team's direction. The modernize analyzer exists to automatically update existing code to use newer idioms (see this talk from the Go team). These guidelines serve the same goal for new code: agents write modern Go from the start, so there's less to fix later. Requirements The marketplace integrations run a small CLI that is installed on first use with go install. Because of that, the Go toolchain must be installed and available on your PATH. The CLI is installed into a local cache (for example ~/.cache/go-modern-guidelines) and never modifies your project. It targets Go 1.25 or newer; on an older Go it still works as long…[truncated]

OpenMontage 号称首个开源 agentic 视频制作系统，通过 12 条 pipeline 与 500+ agent 技能，让 AI 助手完成从调研、脚本、素材生成到剪辑合成的全流程。它区别于普通图生视频工具，能调用免费影像素材库进行真实剪辑与渲染，案例显示 60 秒动画短片成本仅 1.33 美元。

abi/screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue) https://screenshottocode.com screenshot-to-code Convert screenshots, mockups, Figma designs, and screen recordings into clean, functional code using AI. The easiest way to try this is using the official, hosted product at screenshottocode.com → https://github.com/user-attachments/assets/ec08a5e6-9606-41c5-b03a-1bf47dfeba75 Supported stacks: HTML + Tailwind HTML + CSS React + Tailwind Vue + Tailwind Bootstrap Ionic + Tailwind Default AI models: Gemini 3 Flash Preview and Gemini 3.1 Pro Preview - the best models GPT-5.5 and GPT-5.4 Mini Claude Opus 4.6, Claude Opus 4.8 z-image-turbo (using Replicate) for image generation See the Examples section below for more demos. Screenshot to Code also supports taking a screen recording of a website in action and turning that into a functional prototype. 🛠 Getting Started Choose the path that fits what you want to do: Run locally: best if you want to customize, self-host, or contribute. Use the hosted app: the fastest way to try Screenshot to Code with no local setup. Open the hosted app → Running locally requires API keys and a backend/frontend setup. The app has a React/Vite frontend and a FastAPI backend. API keys You need at least one model provider key (OpenAI, Anthropic, or Gemini). Gemini and Replicate are strongly recommended for the best quality of screenshot-to-code accuracy — Gemini powers asset extraction (reusing the real logos/images from your screenshot) and Replicate powers image generation, background removal, and image editing. Adding all four keys gives the best results and lets you compare multiple models per generation. Key Required? What it unlocks OPENAI_API_KEY One of these three GPT code-gen variants (GPT-5.5, GPT-5.4 Mini) ANTHROPIC_API_KEY One of these three Claude code-ge…[truncated]

Cursor 在 GitHub 发布插件规范及首批官方插件，涵盖 Agent 增量记忆、PR 可视化审查、CLI 设计模式等。这标志着 Cursor 从封闭编辑器转向可扩展平台，设计工程师可将内部工作流、代码审查标准固化为插件，直接驱动 AI Agent。

这是一个面向 GPT-Image 2 的 Prompt as Code 开源项目，聚合了 470+ 逆向工程案例与 20+ 工业级模板，配套可视化网站支持直接预览、复制提示词并在线测试。设计师可跳过从零调试，直接复用经商业验证的生成策略，快速落地高完成度的 AI 图像工作流。

tailscale/tailcat

like netcat, but over Tailscale's data plane, without Tailscale's control plane https://tailscale.com/tailcat "Tailscale without Tailscale, by Tailscale" Tailcat Tailcat is a remix of Tailscale open source pieces to act like netcat, but over Tailscale's data plane, without Tailscale's control plane. Tailscale's data plane (magicsock, internally) gives you point-to-point WireGuard®-encrypted tunnels between two machines with DERP as the NAT-hole-punching communication side channel and the ultimate relay-of-last-resort if NAT traversal fails. Instead of using the Tailscale control plane, all tailcat connection metadata is exchanged out of band, however you want. The tailcat CLI (in cmd/tailcat) is built on the tailcat Go library (importable as github.com/tailscale/tailcat). Whether you use tailcat as a CLI tool or library, one side runs a tailcat server (listener) and gets back a short connection token. The other side passes that token to tailcat's client side to connect. All traffic between the two is encrypted end-to-end with WireGuard. The initial connection bootstraps through a DERP server (see below), and then magicsock performs NAT traversal to upgrade to a direct peer-to-peer UDP connection when possible (usually!). You don't need a Tailscale account, root/admin access on the machine (it doesn't alter your machine's routing tables, DNS, etc.). It's just a userspace library and CLI tool. And it's all open source. You can use our free rate-limited DERP relays (the default DERP map is https://tailcat.dev/derpmap.json) or you can run your own. There's also an experimental in-browser web demo (tailcat compiled to WebAssembly) at https://tailscale.github.io/tailcat/ that can send and receive files or text, interoperating with the CLI. Browser traffic is relayed over DERP only, with no direct connections until WebRTC support (#4). Install $ go install github.com/tailscale/tailcat/cmd/tailcat@latest Or with Nix flakes, run it directly or in…[truncated]

NationalSecurityAgency/ghidra

Ghidra is a software reverse engineering (SRE) framework https://www.nsa.gov/ghidra Ghidra Software Reverse Engineering Framework Ghidra is a software reverse engineering (SRE) framework created and maintained by the National Security Agency Research Directorate. This framework includes a suite of full-featured, high-end software analysis tools that enable users to analyze compiled code on a variety of platforms including Windows, macOS, and Linux. Capabilities include disassembly, assembly, decompilation, graphing, and scripting, along with hundreds of other features. Ghidra supports a wide variety of processor instruction sets and executable formats and can be run in both user-interactive and automated modes. Users may also develop their own Ghidra extension components and/or scripts using Java or Python. In support of NSA's Cybersecurity mission, Ghidra was built to solve scaling and teaming problems on complex SRE efforts, and to provide a customizable and extensible SRE research platform. NSA has applied Ghidra SRE capabilities to a variety of problems that involve analyzing malicious code and generating deep insights for SRE analysts who seek a better understanding of potential vulnerabilities in networks and systems. If you are a U.S. citizen interested in projects like this, to develop Ghidra and other cybersecurity tools for NSA to help protect our nation and its allies, consider applying for a career with us. Security Warning WARNING: There are known security vulnerabilities within certain versions of Ghidra. Before proceeding, please read through Ghidra's Security Advisories for a better understanding of how you might be impacted. Install To install an official pre-built multi-platform Ghidra release: Install JDK 21 64-bit Download a Ghidra release file NOTE: The official multi-platform release file is named ghidra_<version>_<release>_<date>.zip which can be found under the "Assets" drop-down. Downloading either of the …[truncated]

Marin 是一个聚焦大语言模型训练全流程的开源框架，涵盖数据筛选、预训练、后训练及评估，并强调实验过程的完全公开。虽然登上 GitHub 热榜，但它属于底层科研基础设施，对设计师日常工作流几乎没有可直接落地的价值。

这是一个开源 API 聚合器，将 34 家提供商的 635 个免费 LLM 端点统一为 OpenAI 兼容格式，支持智能路由与自动故障转移。设计工程师只需一个密钥即可零成本实验各类生成模型，涵盖聊天、图像、音频与嵌入接口，充分利用每月 74 亿 token 的免费额度。

ChromeDevTools/chrome-devtools-mcp

Chrome DevTools for coding agents Chrome DevTools for agents Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. A CLI is also provided for use without MCP. Tool reference | Changelog | Contributing | Troubleshooting | Design Principles Key features Get performance insights: Uses Chrome DevTools to record traces and extract actionable performance insights. Advanced browser debugging: Analyze network requests, take screenshots and check browser console messages (with source-mapped stack traces). Reliable automation. Uses puppeteer to automate actions in Chrome and automatically wait for action results. Disclaimers chrome-devtools-mcp exposes content of the browser instance to the MCP clients allowing them to inspect, debug, and modify any data in the browser or DevTools. Avoid sharing sensitive or personal information that you don't want to share with MCP clients. chrome-devtools-mcp officially supports Google Chrome and Chrome for Testing only. Other Chromium-based browsers may work, but this is not guaranteed, and you may encounter unexpected behavior. Use at your own discretion. We are committed to providing fixes and support for the latest version of Extended Stable Chrome. Performance tools may send trace URLs to the Google CrUX API to fetch real-user experience data. This helps provide a holistic performance picture by presenting field data alongside lab data. This data is collected by the Chrome User Experience Report (CrUX). To disable this, run with the --no-performance-crux flag. Usage statistics Google collects usage statistics (such as tool invocation success rates, latency, and environment information) to improve …[truncated]

GitHub Trending 新晋全开源AI工程课程，共435节课、20个阶段约320小时，覆盖Python/TypeScript/Rust/Julia。课程要求从线性代数和反向传播开始手写代码，逐步构建Tokenizer、Attention机制直至MCP服务器和自主智能体集群，每节课均产出可复用工程产物。

Ponytail 是一套可复用的 AI Agent 提示框架，通过注入“极简主义资深开发者”人格，迫使 Claude Code 等工具用最少代码解决问题。作者在真实 FastAPI + React 仓库上实测，平均减少 54% 代码量、20% 成本并提升 27% 速度，同时保留了完整的安全护栏。

google/googletest

GoogleTest - Google Testing and Mocking Framework https://google.github.io/googletest/ GoogleTest Announcements Documentation Updates Our documentation is now live on GitHub Pages at https://google.github.io/googletest/. We recommend browsing the documentation on GitHub Pages rather than directly in the repository. Release 1.18.0 Release 1.18.0 is now available. The 1.18.x branch requires at least C++17. Continuous Integration We use Google's internal systems for continuous integration. Coming Soon We are planning to take a dependency on Abseil. Welcome to GoogleTest, Google's C++ test framework! This repository is a merger of the formerly separate GoogleTest and GoogleMock projects. These were so closely related that it makes sense to maintain and release them together. Getting Started See the GoogleTest User's Guide for documentation. We recommend starting with the GoogleTest Primer. More information about building GoogleTest can be found at googletest/README.md. Features xUnit test framework: Googletest is based on the xUnit testing framework, a popular architecture for unit testing. Test discovery: Googletest automatically discovers and runs your tests, eliminating the need to manually register your tests. Rich set of assertions: Googletest provides a variety of assertions, such as equality, inequality, exceptions, and more, making it easy to test your code. User-defined assertions: You can define your own assertions with Googletest, making it simple to write tests that are specific to your code. Death tests: Googletest supports death tests, which verify that your code exits in a certain way, making it useful for testing error-handling code. Fatal and non-fatal failures: You can specify whether a test failure should be treated as fatal or non-fatal with Googletest, allowing tests to continue running even if a failure occurs. Value-parameterized tests: Googletest supports value-par…[truncated]

LiveKit Agents 是一个开源框架，用于构建能听、能看、能对话的实时多模态 AI 代理。它支持 STT/LLM/TTS 灵活替换、原生 MCP 工具集成、语义轮次检测及电话接入，适合需要低延迟语音交互的产品原型与工程实现。