skills.rest
ComposioHQ
ComposioHQOFFICIAL
Explore all skills by this author โ†’
Website๐•@composioGitHub

Apify Automation

Automate web scraping and data extraction tasks using the Apify platform and Composio integration.

74.2k|8.5k|Updated Oct 17, 2025
Search Tags:#mcp#web crawling#scraping#Automation#APIFY#Data extraction
One-click install
npx skills add https://github.com/ComposioHQ/awesome-claude-skills --skill apify-automation
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: Apify Automation
Source: https://github.com/ComposioHQ/awesome-claude-skills/tree/main/composio-skills/apify-automation
Command: npx skills add https://github.com/ComposioHQ/awesome-claude-skills --skill apify-automation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual overhead of configuring, running, and monitoring web scrapers, allowing you to extract structured data from the web directly through your AI agent.

Core Features & Use Cases

  • Synchronous Scraping: Execute Actors and retrieve dataset results in a single command for immediate data access.
  • Asynchronous Task Management: Trigger long-running crawlers and manage datasets or reusable tasks without blocking your workflow.
  • Use Case: Automatically scrape product pricing from e-commerce sites or gather search results for market research and feed the structured JSON output directly into your analysis pipeline.

Quick Start

Run the Apify Actor 'compass/crawler-google-places' with the input query 'restaurants in New York' and return the first 50 results.

Frequently Asked Questions about Apify Automation

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

FAQPage Schema
How do I run an Apify Actor and get results immediately?โ–ผ

Use the APIFY_RUN_ACTOR_SYNC_GET_DATASET_ITEMS tool to execute an Actor and retrieve its dataset items in a single call. This is ideal for quick scraping jobs where you need the output immediately.

What should I do if my Actor run takes longer than 5 minutes?โ–ผ

The synchronous tool has a 300-second timeout. For longer runs, use APIFY_RUN_ACTOR to trigger the job asynchronously, then poll for results using APIFY_GET_DATASET_ITEMS once the run completes.

How do I handle different input schemas for various Actors?โ–ผ

Every Actor has a unique input schema. Always check the Actor's page on the Apify Store to identify the exact field names and required data structures before running the tool.

Can I automate recurring scraping tasks?โ–ผ

Yes, use APIFY_CREATE_TASK to configure reusable tasks with preset inputs. This allows you to trigger consistent scraping jobs repeatedly without re-entering configuration parameters.

What are the limitations of dataset retrieval?โ–ผ

The APIFY_GET_DATASET_ITEMS tool has a maximum limit of 1000 items per request. For larger datasets, you must implement pagination by using the offset parameter in subsequent calls.

Related Skills

Explore More Data & Analytics Skillsโ†’
robomotioniorobomotionio
2

apify

Run Apify actors via Robomotion CLI and retrieve datasets.

Official
Intermediate
semicolon-devteamsemicolon-devteam

summarize-meeting

Summarize STT transcripts and meeting notes into discussion and decision summaries.

Official
Advanced
jayjpatel9717jayjpatel9717

sentiment-analysis

Analyze financial news and social media sentiment with Python libraries.

Community
Advanced
npc-chrisnpc-chris
1

browse

Automate headless browser navigation, form interaction, and screenshot comparison for QA testing.

Community
Advanced