Apify

Customization

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Apify/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

You MUST send this notification BEFORE doing anything else when this skill is invoked.

1. Send voice notification:

   curl -s -X POST http://localhost:31337/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow in the Apify skill to ACTION"}' \
     > /dev/null 2>&1 &
   

2. Output text notification:

   Running the **WorkflowName** workflow in the **Apify** skill to ACTION...
   

This is not optional. Execute this curl command immediately upon skill invocation.

Apify - Social Media & Web Scraping

What It Does

Scrapes social platforms, business data, and e-commerce through Apify actors: Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps business search, Amazon, and general-purpose web crawling. TypeScript wrappers filter and transform the data in code before any of it reaches the model, so a 100-post scrape costs roughly what 10 posts would. Runs platforms in parallel for social-listening dashboards and chains Google Maps into LinkedIn for lead enrichment.

The Problem

Scraping through a raw MCP dumps every unfiltered result straight into model context — a single Instagram profile with 100 posts burns ~52,000 tokens, most of it noise you'll throw away. You usually want the top 10 posts, the negative reviews from the last week, the qualified leads with an email. Doing that filtering after the data hits the model is too late; the tokens are already spent. Filtering in code first cuts that 52,000 down to ~500.

How It Works

This skill is a file-based MCP — a code-first API wrapper that replaces token-heavy MCP protocol calls. You call an actor wrapper, filter and sort the result in TypeScript, and only the filtered slice reaches model context. That code-before-context step is where the 95-99% token savings come from.