Why use this instead of Claude's built-in web fetch?

This skill acts as a hardened fallback for URLs that may block standard AI crawlers or when you require more precise Markdown formatting through the Gemini model.

Can I filter specific content on a webpage?

Yes, you can provide an optional instruction after the URL to tell the skill exactly what to focus on, such as 'extract only the installation steps'.

Do I need to install anything extra for this skill?

Yes, you must have the Gemini CLI installed on your system via 'npm i -g @google/gemini-cli' and a valid API key configured.

Does it work with websites that require a login?

Currently, this skill is designed for publicly accessible URLs. Pages behind authentication or paywalls will generally not be accessible.

Web Content Fetcher via Gemini

Name: Web Content Fetcher via Gemini
Author: Dokkabei97

byDokkabei97

•

웹 스크래핑 및 데이터 수집

Fetches and converts web page content into clean Markdown using the Gemini CLI as a robust alternative to native browsing tools.

This skill provides a high-reliability fallback for Claude's native web browsing capabilities by leveraging the Gemini CLI to retrieve and process URL content. Designed for enterprise-grade reliability, it intelligently extracts main body text while stripping away noise like navigation bars, ads, and footers. It is particularly useful when standard tools fail to access specific URLs or when you need to target specific data points, such as API reference tables or documentation sections, using custom extraction instructions.

주요 기능

01Converts complex HTML into clean, structured Markdown automatically.

02Uses high-speed Gemini Flash models to ensure low-latency content fetching.

03Supports custom extraction instructions for targeted data retrieval from pages.

042 GitHub stars

05Intelligently filters out non-essential elements like ads, sidebars, and footers.

06Acts as a reliable fallback when native Claude WebFetch tools are blocked or fail.

사용 사례

01Retrieving technical documentation from websites where standard scrapers are blocked.

02Consolidating web-based research directly into the Claude Code environment for analysis.

03Extracting specific code blocks or API reference tables from long-form technical articles.

주요 기능

01Converts complex HTML into clean, structured Markdown automatically.

02Uses high-speed Gemini Flash models to ensure low-latency content fetching.

03Supports custom extraction instructions for targeted data retrieval from pages.

042 GitHub stars

05Intelligently filters out non-essential elements like ads, sidebars, and footers.

06Acts as a reliable fallback when native Claude WebFetch tools are blocked or fail.

사용 사례

01Retrieving technical documentation from websites where standard scrapers are blocked.

02Consolidating web-based research directly into the Claude Code environment for analysis.

03Extracting specific code blocks or API reference tables from long-form technical articles.