How do I find the correct input schema for a specific Actor?

Use the APIFY_GET_ACTOR tool to inspect the metadata and input requirements for any specific Apify Actor, ensuring you provide the exact field names expected.

Can I run Apify Actors asynchronously?

Yes, you can trigger Actors to run in the background using the APIFY_RUN_ACTOR tool and retrieve results later using the dataset ID once the run is complete.

Does this skill require an Apify account?

Yes, you will need an active Apify account. You will be prompted to connect it via a secure authentication link when you first set up the Composio MCP server.

What is the maximum number of items I can retrieve at once?

The skill supports retrieving up to 1000 items per call. For larger datasets, you can use the offset parameter to paginate through the data.

Apify Automation for Claude Code

Name: Apify Automation for Claude Code
Author: hameed0342j

byhameed0342j

0•

网络抓取与数据收集

Automates web scraping and data extraction by running Apify Actors and managing datasets directly within your terminal.

This skill integrates the powerful Apify platform with Claude Code, allowing developers to execute complex web scraping Actors, manage large datasets, and retrieve structured data without leaving the terminal. It supports both synchronous and asynchronous execution, provides deep access to Actor metadata and input schemas, and includes tools for managing reusable tasks and execution logs. Whether you are scraping search engine results, extracting e-commerce data, or monitoring website changes, this skill provides a professional-grade workflow for high-scale data collection within your AI-driven development environment.

主要功能

01Actor input schema discovery to ensure correct parameter usage

02Direct access to execution logs for debugging and monitoring

030 GitHub stars

04Reusable task management for recurring data collection workflows

05Automated dataset retrieval with support for JSON, CSV, and XLSX formats

06Synchronous and asynchronous Actor execution for long-running scraping jobs

使用场景

01Extracting competitor pricing or product information for real-time market analysis

02Generating high-quality structured training data for machine learning models from web sources

03Automating lead generation by scraping business directories like Google Maps or LinkedIn

主要功能

01Actor input schema discovery to ensure correct parameter usage

02Direct access to execution logs for debugging and monitoring

030 GitHub stars

04Reusable task management for recurring data collection workflows

05Automated dataset retrieval with support for JSON, CSV, and XLSX formats

06Synchronous and asynchronous Actor execution for long-running scraping jobs

使用场景

01Extracting competitor pricing or product information for real-time market analysis

02Generating high-quality structured training data for machine learning models from web sources

03Automating lead generation by scraping business directories like Google Maps or LinkedIn