scrape
Scrape a single webpage and extract its content as markdown, HTML, JSON, or text using Olostep
Install
With your agent
Install OMGSkills skill "olostep/olostep-claude-code-plugin:skills/scrape" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/olostep/olostep-claude-code-plugin /tmp/olostep-claude-code-plugin && ln -s /tmp/olostep-claude-code-plugin/skills/scrape ~/.claude/skills/scrapeFrom README
Olostep Scrape Extract content from a single webpage URL using Olostep's web scraping API with JavaScript rendering and anti-bot handling. Instructions When the user provides a URL (via $ARGUMENTS or in conversation): Use the mcpolostepscrapewebsite tool to scrape the URL. Default to markdown format unless the user specifies otherwise (html, json, text). If the page has dynamic content, suggest using waitbeforescraping (e.g., 2000ms). If the user needs geo-targeted content, ask for a country code (e.g., US, GB, CA).