midscene-computer-browser
由 quanru 提供
Web & Frontend Development简介
Vision-driven browser automation using Midscene.
描述
该技能的功能
Vision-driven browser automation that operates from screenshots alone, without needing DOM access or accessibility labels. Launches headless Chrome via Puppeteer and interacts with any visible page element using natural language instructions. Works across any frontend technology stack.
Works from screenshots alone, so it handles any frontend stack without needing DOM access, custom selectors, or accessibility attributes.
何时使用
- Scraping product prices from e-commerce pages
- Filling and submitting multi-step online forms
- Taking screenshots of web pages for review or archiving
- Verifying UI behavior after a deployment
- Extracting data from paginated tables or dashboards
示例工作流
User asks: Get the titles of the top 5 articles on Hacker News
- 1
Connect to https://news.ycombinator.com
- 2
Take a screenshot to confirm the page has loaded
- 3
Act: read the titles of the top 5 articles from the page
- 4
Close the browser
List of the top 5 Hacker News article titles extracted from the page
前置要求
- MIDSCENE_MODEL_API_KEY environment variable (API key from a supported vision model provider)
- MIDSCENE_MODEL_NAME environment variable
- MIDSCENE_MODEL_BASE_URL environment variable
- MIDSCENE_MODEL_FAMILY environment variable
安装
clawhub install quanru/midscene-computer-browser运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。