This skill enables users to extract clean content like markdown, HTML, or JSON from one or more URLs using the Bright Data CLI. It is suitable for developers and data analysts needing to fetch raw or lightly structured content.
$ npx skills add https://github.com/brightdata/skills --skill scrapeThe Bright Data Scrape skill enables extraction of webpage content in multiple formats—markdown, HTML, or JSON—using Bright Data's Web Unlocker infrastructure. It automatically handles bot detection bypass and CAPTCHA circumvention, allowing reliable access to any webpage without manual intervention. The skill integrates with the Bright Data CLI, letting users scrape directly from the terminal with the `brightdata` or `bdata` commands. Developers and data analysts use this to build data pipelines, conduct competitive research, or feed content into RAG systems and AI workflows. It supports both synchronous requests and asynchronous polling for larger scraping jobs.
Use the command `npx skills add https://github.com/brightdata/skills --skill scrape` to install.
Extracting HTML content for web analysis
Saving scraped data in JSON format for further processing
Taking screenshots of web pages for visual documentation
Fetching data from various platforms without the need for complex selectors
$ npx skills add https://github.com/brightdata/skills --skill scrapegit clone https://github.com/brightdata/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan