> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scrapegraphai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code Skill

> Give Claude Code and AI coding agents the power of web scraping

## Overview

The ScrapeGraphAI Claude Code Skill ships with [just-scrape](https://github.com/ScrapeGraphAI/just-scrape), the official CLI for the **v2 API**. Once installed, agents like Claude Code, Cursor, Copilot, Cline, and Windsurf can scrape websites, extract structured data, search the web, crawl sites, and set up page-change monitors — all from natural language prompts.

The skill wires `just-scrape` into your agent's skill directory so the agent knows when and how to invoke the CLI.

<Card title="GitHub Repository" icon="github" href="https://github.com/ScrapeGraphAI/just-scrape">
  Browse the CLI and skill source
</Card>

## Installation

<Steps>
  ### Option 1: Install via skills.sh (Recommended)

  The fastest way to install. Requires [Node.js](https://nodejs.org) or [Bun](https://bun.sh).

  ```bash theme={null}
  bunx skills add https://github.com/ScrapeGraphAI/just-scrape
  # or
  npx skills add https://github.com/ScrapeGraphAI/just-scrape
  ```

  This symlinks `skills/just-scrape/SKILL.md` into your `~/.claude/skills/` directory automatically.

  You can also browse the published skill at [skills.sh/scrapegraphai/just-scrape/just-scrape](https://skills.sh/scrapegraphai/just-scrape/just-scrape).

  ### Option 2: Manual install

  Clone the repository and create the symlink yourself:

  ```bash theme={null}
  git clone https://github.com/ScrapeGraphAI/just-scrape.git ~/.claude/skills/just-scrape
  ln -sf ~/.claude/skills/just-scrape/skills/just-scrape/SKILL.md ~/.claude/skills/just-scrape.md
  ```

  ### Option 3: Project-level install

  Install the skill for a single project only:

  ```bash theme={null}
  mkdir -p .claude/skills
  git clone https://github.com/ScrapeGraphAI/just-scrape.git .claude/skills/just-scrape
  ln -sf .claude/skills/just-scrape/skills/just-scrape/SKILL.md .claude/skills/just-scrape.md
  ```
</Steps>

## Setup

Install the CLI and set your ScrapeGraphAI API key:

```bash theme={null}
npm install -g just-scrape@latest
export SGAI_API_KEY="sgai-..."
```

<Note>
  Get your API key from the [dashboard](https://scrapegraphai.com/dashboard). The CLI also accepts the key via a `.env` file, `~/.scrapegraphai/config.json`, or an interactive prompt.
</Note>

## Capabilities

The skill maps to the v2 API surface via `just-scrape`:

<CardGroup cols={2}>
  <Card title="extract" icon="wand-magic-sparkles">
    Extract structured data from any URL using AI (`just-scrape extract`)
  </Card>

  <Card title="search" icon="magnifying-glass">
    Search the web and extract structured results (`just-scrape search`)
  </Card>

  <Card title="scrape" icon="file-code">
    Fetch a page in 8 formats: markdown, html, screenshot, branding, links, images, summary, json
  </Card>

  <Card title="markdownify" icon="file-lines">
    Convert any webpage into clean markdown (wraps `scrape -f markdown`)
  </Card>

  <Card title="crawl" icon="spider">
    Crawl multi-page sites with depth, link, and pattern controls
  </Card>

  <Card title="monitor" icon="clock">
    Schedule page-change monitors with cron intervals, webhooks, and activity polling
  </Card>
</CardGroup>

<Note>
  Removed from v1: `sitemap`, `agentic_scraper`, `generate-schema`, `validate`. There is no direct replacement on v2.
</Note>

## Example Prompts

Once the skill is installed, you can use natural language prompts directly in your AI coding agent:

```text theme={null}
Scrape https://example.com/products and extract all product names, prices, and ratings
```

```text theme={null}
Search the web for "best React UI libraries 2025" and extract the top 5 with pros and cons
```

```text theme={null}
Convert https://example.com/docs/getting-started to markdown and save it to docs/
```

```text theme={null}
Crawl https://example.com/blog with depth 2 and extract the title and summary from each post
```

```text theme={null}
Monitor https://store.example.com/pricing every hour and webhook me when it changes
```

```text theme={null}
Create a 30m monitor on https://example.com and poll its activity feed, printing new ticks as they come in
```

```text theme={null}
Fetch a full-page screenshot and branding assets for https://example.com
```

The agent will automatically select the right `just-scrape` command, handle authentication, poll for async results (crawls), and return structured data.

## Supported Agents

This skill works with any AI coding agent that supports the skills protocol:

* **Claude Code** — Anthropic's CLI agent
* **Cursor** — AI-powered code editor
* **GitHub Copilot** — AI pair programmer
* **Cline** — VS Code AI agent
* **Windsurf** — AI coding assistant
* And any other agent supporting [skills.sh](https://skills.sh)

## Support

Need help with the skill?

<CardGroup cols={2}>
  <Card title="GitHub Issues" icon="github" href="https://github.com/ScrapeGraphAI/just-scrape/issues">
    Report bugs and request features
  </Card>

  <Card title="Discord Community" icon="discord" href="https://discord.gg/uJN7TYcpNa">
    Get help from our community
  </Card>
</CardGroup>