crawler

Crawl websites to discover APIs, cookies, tokens, and headers and generate structured artifacts.

1|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/moveonha/pixel-ai-studio --skill crawler-moveonha
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: crawler
Source: https://github.com/moveonha/pixel-ai-studio/tree/main/.claude/skills/crawler
Command: npx skills add https://github.com/moveonha/pixel-ai-studio --skill crawler-moveonha

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Crawling websites to systematically discover APIs, cookies, tokens, and headers and document findings for reproducibility and knowledge transfer.

Core Features & Use Cases

  • Guided, hands-on approach to exploring sites and documenting API surfaces, authentication details, and HTTP headers.
  • Generates structured artifacts under .claude/crawler/[site]/ including ANALYSIS.md, SELECTORS.md, API.md, NETWORK.md, and CRAWLER.ts for code generation.
  • Use cases include rapid reconnaissance, API mapping, and automated crawler code creation for repeatable workflows.

Quick Start

Run a Playwriter session, navigate to a target site, and let the tool build the crawler documentation and starter code for a new site.

Frequently Asked Questions about crawler

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

FAQPage Schema
How do I discover APIs and extract authentication tokens during web scraping?

Web scraping API discovery involves crawling target sites to systematically capture APIs, cookies, tokens, and headers. This tool automates that reconnaissance using Playwriter sessions and accessibility snapshots to document findings for reproducibility.

What is the best way to document web crawling findings for API mapping?

Documenting web crawling findings requires generating structured artifacts like ANALYSIS.md, SELECTORS.md, API.md, NETWORK.md, and CRAWLER.ts. This approach creates reproducible API mapping records and starter code under a dedicated site directory.

Can I use Playwright to intercept network requests and map API endpoints automatically?

Yes, running a Playwriter session enables network request interception to map API endpoints, extract authentication details, and capture HTTP headers. It automatically generates crawler templates and structured documentation for the discovered site.

Do I need any dependencies to generate crawler templates and document website APIs?

No external dependencies are required to generate crawler templates and document website APIs. You only need a Playwriter session environment to navigate the target site and trigger the automated artifact generation workflow.

How do I start automated crawler code creation for a new website?

To start automated crawler code creation, run a Playwriter session and navigate to your target site. The tool then builds the crawler documentation, network analysis, and CRAWLER.ts starter code for repeatable workflows.

Why generate structured artifacts like SELECTORS.md and NETWORK.md during web reconnaissance?

Generating structured artifacts like SELECTORS.md and NETWORK.md during web reconnaissance ensures reproducibility and knowledge transfer. It captures API surfaces, authentication details, and HTTP headers in a standardized format for automated crawler workflows.