scrape-do-automation

Automate web scraping operations through the Scrape Do toolkit via Rube MCP.

74.2k|8.5k|Updated Oct 17, 2025
One-click install
npx skills add https://github.com/ComposioHQ/awesome-claude-skills --skill scrape-do-automation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrape-do-automation
Source: https://github.com/ComposioHQ/awesome-claude-skills/tree/main/composio-skills/scrape-do-automation
Command: npx skills add https://github.com/ComposioHQ/awesome-claude-skills --skill scrape-do-automation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the complexity of manually configuring and executing web scraping tasks by providing a standardized interface for interacting with Scrape Do via the Rube MCP gateway.

Core Features & Use Cases

  • Tool Discovery: Dynamically fetch current tool schemas and execution plans for Scrape Do.
  • Connection Management: Handle authentication and session state for Scrape Do toolkits.
  • Execution: Perform multi-step scraping workflows including bulk operations and remote workbench tasks.

Quick Start

Use the scrape-do-automation skill to discover available tools and execute a scraping task for the target URL.

Frequently Asked Questions about scrape-do-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I start a scraping task with Scrape Do?

Begin by calling RUBE_SEARCH_TOOLS to identify available scraping tools, then use RUBE_MANAGE_CONNECTIONS to ensure your Scrape Do toolkit is active before executing your task.

What should I do if my scraping tool schema changes?

Always call RUBE_SEARCH_TOOLS before executing any workflow to retrieve the most current tool slugs, input schemas, and execution parameters.

Can I reuse session IDs for multiple scraping tasks?

Reuse session IDs within a single workflow for consistency, but generate new session IDs for distinct, unrelated scraping tasks to maintain clean state management.

Why is the memory parameter required in RUBE_MULTI_EXECUTE_TOOL?

The memory parameter is a mandatory field for RUBE_MULTI_EXECUTE_TOOL calls, even if it is empty, to ensure compatibility with the Rube MCP execution engine.

How do I handle large-scale scraping with this skill?

Use RUBE_REMOTE_WORKBENCH with the run_composio_tool() function to perform bulk operations and check responses for pagination tokens to continue fetching data until complete.