Zyte Web Data

This file is 214 lines long; read all of them.

<p align="center"> <img src="assets/zyte-logo.png" alt="Zyte" width="180"> </p>

<h1 align="center">Zyte Agentic Web Data for Claude Code</h1>

<p align="center"> From a plain-English prompt to a working Scrapy spider. </p>

<p align="center"> <a href="https://github.com/zytedata/claude-skills/releases/tag/0.4.0"> <img src="https://img.shields.io/badge/version-0.4.0-blue" alt="Version 0.4.0"> </a> <a href="https://github.com/zytedata/claude-skills/blob/main/LICENSE.md"> <img src="https://img.shields.io/badge/license-Zyte EULA-b02cce" alt="Zyte EULA"> </a> <a href="https://github.com/zytedata/claude-skills"> <img src="https://img.shields.io/github/stars/zytedata/claude-skills?style=social" alt="GitHub stars"> </a> </p>

---

Not using exclusively Claude Code? See Zyte Coding Agent Add-Ons for alternatives.

Install

claude plugin marketplace add zytedata/claude-skills
claude plugin install zyte-web-data@zyte-ai

If Claude Code is already running, reload plugins in the active session:

/reload-plugins

If /reload-plugins isn't available (e.g. in the VS Code extension), restart Claude Code.

See also: Discovering and installing plugins

The plugin declares the Zyte MCP server itself, so do not add it with claude mcp add as well. Sign in to it once, in the browser, from an active session:

/mcp

---

What it does

This is Zyte's official Claude Code plugin that generates production-ready Scrapy spiders with web-poet page objects from a plain-English prompt. Give it a URL and describe what you want to extract. It handles site exploration, schema discovery, code generation, and smoke testing: no boilerplate, no manual selector hunting.

The plugin explores the target site, discovers available fields, and presents a schema for your approval before generating a single line of code. After you confirm the schema, it creates a Scrapy project with all dependencies configured, generates web-poet page objects and test fixtures, wires up the spider, and runs a smoke test to verify that extraction is working before handing the project back to you.