Xcrawl Scrape

A straightforward wrapper around XCrawl's single-page scrape API that lets Claude fetch and parse web content through curl and node commands. You get markdown, HTML, links, screenshots, or structured JSON extraction via prompt or schema, all configurable through a single POST endpoint. The skill enforces local API key storage in ~/.xcrawl/config.json and sticks to raw response passthrough by default, so you see exactly what the upstream API returns. Works in sync or async mode, supports proxy rotation and browser rendering options, and shows credit consumption per request. Useful when you need Claude to grab structured data from a page without writing your own scraper, though you'll need an XCrawl account with credits to actually run requests.

skills.sh installs: 244
GitHub stars: 449
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add xcrawl-api/xcrawl-skills --skill xcrawl-scrape --agent claude-code

Installs into .claude/skills of the current project.

Files

XCrawl Scrape

Overview

This skill handles single-page extraction with XCrawl Scrape APIs. Default behavior is raw passthrough: return upstream API response bodies as-is.

Required Local Config

Before using this skill, the user must create a local config file and write XCRAWL_API_KEY into it.

Path: ~/.xcrawl/config.json

{
  "XCRAWL_API_KEY": "<your_api_key>"
}

Read API key from local config file only. Do not require global environment variables.

Credits and Account Setup

Using XCrawl APIs consumes credits. If the user does not have an account or available credits, guide them to register at https://dash.xcrawl.com/. After registration, they can activate the free 1000 credits plan before running requests.