[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

DeepSeek Harness Computer Use 插件（Windows）：让 AI 看屏幕、点鼠标、敲键盘操控电脑；控制时屏幕泛起橙色光晕并显示“DeepSeek Harness 正在操控你的电脑”，按 Esc 暂停 / 继续。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Recreate an image, screenshot, or mockup as a 1:1 UI implementation. Match the reference rather than redesigning it, then render and compare the result to correct visible differences.

Drive an app running on a Limrun cloud Android emulator: install an APK, launch and terminate apps with crash reports, tap, type, read the UI element tree, screenshot, record video, inject microphone audio, shape network bandwidth, read app logs, run shell commands, transfer files, tunnel the app's

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Enables MCP clients to review Ceramic and ordinary websites with desktop/mobile browser QA, deterministic design and accessibility checks, optional visual judgement, and repeatable fix verification backed by preserved screenshots and reports.

Enables control of an attached Android phone over ADB, including screenshots, taps, typing, key/chord input via a virtual HID keyboard, UI inspection, and device information without root.

Enables AI clients to control and inspect a Unity Editor through MCP tools for scene and play-mode operations, logs, screenshots, assertions, Lua execution, UI interaction, world observation, and bridge management; advanced UI/Lua/world features require project-specific adapters.

Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.

Enables MCP-capable AI agents to control Windows desktops through UI Automation element trees, native screenshots, app launching, batched action sequences, smart waits, and safety gates using normalized coordinates.

Enables AI assistants to read Lanhu requirements and design handoffs, extract pages, annotations, screenshots, design parameters, and image assets, and share team knowledge through a collaborative message board.

Claude Design: AI UI/UX architect. Screenshot to React, Figma components, Tailwind CSS generator. Prototyping agent, design systems, wireframe renderer. SVG icon creator, dark mode toggle, responsive layout tool. Front-end code export, shadcn/ui integration, vector assets, branding assistant.