Does it support websites that require a login?

No, this skill is designed for publicly accessible URLs. It does not currently support authentication or session-based browsing.

Why use this over Claude's built-in WebFetch tool?

This skill serves as a high-reliability fallback when native tools fail due to site restrictions or technical errors, often providing cleaner Markdown output and better noise reduction.

Which AI model powers the fetching process?

It utilizes the gemini-3.1-flash-preview model to ensure maximum speed and efficiency while maintaining high accuracy in Markdown conversion.

Can I extract specific parts of a page instead of the whole thing?

Absolutely. The skill accepts an optional extraction instruction argument that allows you to specify exactly what content, such as a specific table or section, you want to focus on.

Do I need any external tools installed to use this?

Yes, this skill requires the Gemini CLI to be installed globally on your system via 'npm i -g @google/gemini-cli' and configured with a valid API key.

Web Fetch via Gemini CLI

Name: Web Fetch via Gemini CLI
Author: Dokkabei97

byDokkabei97

•

Web Scraping & Data Collection

Fetches and converts web content into clean Markdown using the Gemini CLI as a reliable fallback for Claude's native tools.

This skill provides a robust alternative for retrieving web content by leveraging the Gemini CLI's native browsing capabilities. It is particularly useful when Claude's internal WebFetch tool fails or encounters restricted access. The skill automatically strips away non-essential elements like advertisements, navigation bars, and footers, delivering structured Markdown that preserves code blocks, tables, and lists. Users can also provide specific extraction instructions to focus on particular sections of a page, such as API reference tables or specific documentation blocks, ensuring high-quality context for development tasks.

Key Features

01Intelligent noise reduction (removes ads, footers, and navs)

02Reliable fallback for failed native web browsing requests

03High-speed processing using Gemini-3.1-Flash models

042 GitHub stars

05Customizable extraction instructions for targeted data scraping

06Automatic conversion of HTML to clean, structured Markdown

Use Cases

01Ingesting web-based research and articles into the AI context without boilerplate

02Retrieving technical documentation or API references when native tools are blocked

03Extracting specific data tables or code examples from complex web pages

Key Features

01Intelligent noise reduction (removes ads, footers, and navs)

02Reliable fallback for failed native web browsing requests

03High-speed processing using Gemini-3.1-Flash models

042 GitHub stars

05Customizable extraction instructions for targeted data scraping

06Automatic conversion of HTML to clean, structured Markdown

Use Cases

01Ingesting web-based research and articles into the AI context without boilerplate

02Retrieving technical documentation or API references when native tools are blocked

03Extracting specific data tables or code examples from complex web pages