name: "Skyvern AI 浏览器工作流自动化与大语言模型和计算机视觉" slug: "skyvern-ai-browser-workflow-automation" version: "1.0.0" displayName: "Skyvern AI 浏览器工作流自动化与大语言模型和计算机视觉" summary: "Skyvern 使用大型语言模型和计算机视觉来自动化基于浏览器的工作流。它提供了一个与 Playwright 兼容的 SDK，该 SDK 通过视觉方式与网站交互，而不是通过 DOM 选择器，这使得自动化操作能够抵抗布局变化，并且能够在以前从未见过的网站上运行。" license: "MIT" description: "Skyvern 使用大型语言模型和计算机视觉来自动化基于浏览器的工作流。它提供了一个与 Playwright 兼容的 SDK，该 SDK 通过视觉方式与网站交互，而不是通过 DOM 选择器，这使得自动化操作能够抵抗布局变化，并且能够在以前从未见过的网站上运行。" github_stars: 20997 verification: "security_reviewed" source: "https://github.com/1991513ccie-png/skills" category: "Browser Automation" framework: "Multi-Framework" tool_ecosystem: github_repo: "1991513ccie-png/skills" github_stars: 20997

Skyvern AI 浏览器工作流自动化与大语言模型和计算机视觉

Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that interacts with websites visually rather than via DOM selectors, making automations resistant to layout changes and capable of operating on never-before-seen websites.

Installation

这个技能的最新版本可以在7w4.net小葱技能站找到。

Use the upstream install or setup path that matches your environment: - pip install skyvern - git clone https://github.com/1991513ccie-png/skills && cd skyvern - docker compose up -d - pip install --upgrade skyvern # 1.0.32+ contains the fix

Requirements and caveats from upstream: - Python 3.11.x, works with 3.12, not ready yet for 3.13 - ### Option B: Docker Compose - Use this option if you want everything containerized (Postgres, API, UI) and don't want to install Python/Node locally.

Basic usage or getting-started notes: - ## Skyvern Cloud - Skyvern Cloud is a managed cloud version of Skyvern that allows you to run Skyvern without worrying about the infrastructure. It allows you to run multiple Skyvern instances in parallel and... - If you'd like to try it out, navigate to app.skyvern.com and create an account.

• Source: https://github.com/1991513ccie-png/skills
• Extracted from upstream docs: https://raw.githubusercontent.com/Skyvern-AI/skyvern/HEAD/README.md

这个 Skill 提供了 Skyvern 浏览器自动化工具的基本说明，安装方式多样（pip/git/ Docker），上手门槛适中。文档内容较为基础，缺少实际使用示例和操作指南，对于初次使用者可能不够友好，需要参考官方文档补充更多信息。总体来说是一个框架性的介绍性 Skill，质量中规中矩，有进一步完善的空间。