Apify

Run Apify actors and filter dataset results in code.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/larsboes/pai-marketplace --skill apify-larsboes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Apify
Source: https://github.com/larsboes/pai-marketplace/tree/main/marketplace/plugins/scraping/skills/Apify
Command: npx skills add https://github.com/larsboes/pai-marketplace --skill apify-larsboes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Replaces token-heavy MCP calls with a code-first interface to Apify actors, ensuring only filtered data enters the model context and dramatically reducing token usage during scraping workflows.

Core Features & Use Cases

  • Code-first access to Apify actors for searching, running, and retrieving results with in-code filtering.
  • Supports social-media scraping (Twitter, Instagram, LinkedIn, TikTok, YouTube, Facebook) and business data (Google Maps, Amazon) for lead generation and analytics.
  • Real-world use case: collect a small, high-signal set of items (profiles, posts, or reviews) and pass only those to the model context.

Quick Start

Run a simple code-first workflow to search for an actor, invoke it with input, wait for completion, fetch the dataset, and filter the results in code before they reach the model.

Frequently Asked Questions about Apify

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

FAQPage Schema
How do I reduce token usage when scraping web data with Apify actors?

Token usage during web scraping is reduced by using a code-first interface to execute Apify actors, fetching datasets, and filtering results in code before the data enters the model context.

Can I scrape social media platforms like Instagram and LinkedIn for lead generation?

Social media scraping for lead generation is supported across platforms like Instagram, LinkedIn, Twitter, TikTok, and YouTube, alongside business data sources such as Google Maps and Amazon.

What is the best way to run Apify actors without overwhelming the model context window?

The best way to manage model context is running Apify actors through a code-first workflow that performs in-code filtering on datasets, ensuring only a small, high-signal set of items reaches the model.

How do I search for and retrieve filtered datasets from Apify?

You search for an actor, invoke it with input, wait for completion, and fetch the dataset. Filtering is then applied directly in code to the retrieved results before they reach the model.

Does this code-first scraping approach work without MCP calls?

Yes, this approach replaces token-heavy MCP calls entirely by executing search, actor runs, dataset retrieval, and in-code filtering directly through a code-first interface.

What are the limitations of using code-first web scraping for data collection?

The primary limitation is that users must handle the code-first execution of actor runs and in-code filtering manually, requiring development knowledge to ensure scalable, privacy-preserving data collection.