A powerful web scraping engine that handles Cloudflare and antibot protections to reliably fetch and structure web data.

Install

mkdir -p .claude/skills/webclaw && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8893" && unzip -o skill.zip -d .claude/skills/webclaw && rm skill.zip

Installs to .claude/skills/webclaw

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Web extraction engine with antibot bypass. Scrape, crawl, extract, summarize, search, map, diff, monitor, research, and analyze any URL — including Cloudflare-protected sites. Use when you need reliable web content, the built-in web_fetch fails, or you need structured data extraction from web pages.
300 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Extract content from URLs including bot-protected sites
  • Crawl entire websites with depth and page limits
  • Perform structured data extraction using JSON schemas
  • Summarize web pages and detect content changes
  • Map site structures to discover all URLs

How it works

The engine uses a local-first approach, falling back to a cloud-based extraction service for JavaScript-rendered or bot-protected pages when an API key is provided.

Inputs & outputs

You give it
URL and optional CSS selectors or extraction schema
You get back
Cleaned Markdown, text, or structured JSON data

When to use webclaw

  • Extracting product pricing tables
  • Crawling entire sites for data
  • Monitoring web content for changes
  • Summarizing long web pages

About webclaw

Extracts content from any URL, including sites with Cloudflare or DataDome protection. It performs scraping, crawling, summarizing, and structured data extraction with built-in antibot bypass.

Web extraction engine with antibot bypass. Scrape, crawl, extract, summarize, search, map, diff, monitor, research, and analyze any URL — including Cloudflare-protected sites. Use when you need reliable web content, the built-in web_fetch fails, or you need structured data extraction from web pages.

When not to use it

  • When simple, fast lookups are sufficient and web_fetch suffices
  • When no WEBCLAW_API_KEY is available for protected sites

Prerequisites

WEBCLAW_API_KEY

Limitations

  • Requires an API key for bot-protected or JavaScript-rendered content
  • Rate limiting is managed server-side

How it compares

Unlike standard fetch tools, this engine includes a 20-step optimization pipeline and cloud-based antibot bypass for reliable data extraction.

Compared to similar skills

webclaw side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
webclaw (this skill)14moReviewIntermediate
scientific-brainstorming377moNo flagsIntermediate
brightdata-web-mcp96moReviewIntermediate
web-scraper01moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry