Apify for Openclaw

Run and manage over 17,000 specialized web scrapers and automation tools via the Apify REST API.

bmestanov
v1.0.3
Feb 14, 2026
7
4k
29

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install apify

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install apify using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Apify?

The Apify skill provides a robust interface to interact with the Apify ecosystem, a platform hosting thousands of ready-made Actors for web scraping, crawling, and browser automation. By utilizing Openclaw Skills, developers can programmatically discover Actors in the Apify Store, inspect their input schemas, and execute them to extract structured data from virtually any website.

This integration allows for both simple synchronous data retrieval and complex asynchronous workflows suitable for large-scale data harvesting. It abstracts the complexities of proxy management, headless browser configuration, and infrastructure scaling, making it an essential tool for data-driven projects and AI agent workflows.

Apify Use Cases

  • Scraping e-commerce product data, pricing, and reviews for market analysis.
  • Extracting search engine results (SERP) for SEO monitoring and research.
  • Automating interactions with web applications that lack official APIs.
  • Collecting large-scale datasets from social media or news outlets for AI model training.

How Apify Works

  1. Search the Apify Store using keywords to find an Actor that matches your specific data extraction needs.
  2. Fetch the Actor's build information to retrieve its README and input JSON schema.
  3. Construct a valid input payload and trigger an Actor run via a POST request.
  4. Monitor the run status for long-running tasks or use synchronous endpoints for quick results.
  5. Access the results from the default dataset in your preferred format like JSON or CSV.

Apify Setup

To use this skill, you must have an active Apify account and an API token. Set the APIFY_TOKEN environment variable in your shell or configuration file. You will also need curl and jq installed for command-line execution and JSON parsing.

export APIFY_TOKEN='your_apify_api_token'

Apify Data Schema & Taxonomy

The skill organizes data through several core Apify API structures to ensure metadata clarity and data integrity.

Entity Description
Actor Run The execution instance of a scraper, containing status and timing metadata.
Dataset A storage collection for structured results, supporting various export formats.
Key-Value Store A storage system for persistent state, screenshots, or binary output files.
Input Schema A definition of the parameters required to configure the Actor's behavior.

Apify Advanced Features

  • Support for asynchronous polling to handle heavy-duty crawling tasks that take time to complete.
  • Synchronous execution endpoints for lightweight scrapers to get results in a single request.
  • Detailed log retrieval for debugging failed Actor runs and monitoring performance.
  • Ability to manage subscriptions and permissions for paid or rental Actors directly through the API.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*