Back to directory

Apify Agent Skills

A collection of Agent Skills giving an AI coding assistant expert use of the Apify web-scraping platform: selecting from more than 130 curated scraping Actors, building and deploying new Actors, wrapping existing code as an Actor, and generating an Actor's input/output schemas.

Apify Agent Skills

Apify Agent Skills installs into Claude Code, Cursor, Windsurf, Codex or Gemini CLI and gives the connected agent working knowledge of the Apify platform, a marketplace for web-scraping and data-extraction tools called Actors. One skill selects from more than 130 curated Actors covering major social, search, maps, real estate and review platforms, falling back to Apify's full store of more than 30,000 Actors for anything else, handling Actor selection, input shaping, run management and result formatting for a plain-language scraping request.

Other skills generate, debug and deploy new serverless Actors in JavaScript, TypeScript or Python using the official SDK patterns, wrap an existing script, library or CLI tool as a runnable Actor, derive an Actor's dataset, output and key-value-store schemas from its source code, and build an official Apify integration for a workflow-automation app, an agent-harness plugin, an AI framework package, or a direct application client.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.