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

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:

这个技能的最新版本可以在7w4.net小葱技能站找到。

• 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。