fetch

Fetch web content from a URL and convert it to Markdown.

1|Updated Jan 30, 2026

Search Tags:#markdown #llm #web scraping #url fetch #content retrieval

Ready to run

npx skills add https://github.com/Svtoo/atk-registry --skill fetch-svtoo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: fetch
Source: https://github.com/Svtoo/atk-registry/tree/main/plugins/fetch
Command: npx skills add https://github.com/Svtoo/atk-registry --skill fetch-svtoo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of retrieving content from web pages, converting it into a clean Markdown format optimized for LLM analysis and quoting, thereby eliminating the need for manual web scraping and HTML parsing.

Core Features & Use Cases

URL Fetching: Retrieves content from any given URL.
HTML to Markdown Conversion: Simplifies HTML into token-efficient Markdown.
Chunked Retrieval: Handles long pages by returning content in paginated chunks.
Use Case: You need to summarize a long article from a news website. Use this Skill to fetch the article's content and get it as clean Markdown, ready for summarization.

Quick Start

Fetch the content of the URL https://example.com and return it as Markdown.

Frequently Asked Questions about fetch

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

FAQPage Schema

How do I convert web page HTML to Markdown for LLM analysis?▼

To convert web page HTML to Markdown for LLM analysis, this Skill fetches content from a specified URL and transforms it into token-efficient Markdown. This eliminates manual web scraping and HTML parsing, providing clean text directly optimized for large language models.

What is the best way to fetch long articles from a URL without truncation?▼

The best way to fetch long articles without truncation is using chunked retrieval. This Skill handles long pages by returning content in paginated chunks, ensuring you receive the complete document structured as Markdown for comprehensive analysis.

Does this URL fetching tool respect robots.txt for model-initiated requests?▼

Yes, this URL fetching tool respects robots.txt for model-initiated requests. Operating via a Model Context Protocol server, it ensures compliant content retrieval and HTML to Markdown conversion without violating site scraping restrictions.

Can I retrieve raw HTML instead of Markdown when fetching web content?▼

Yes, you can retrieve raw HTML instead of Markdown when fetching web content. Alongside default HTML to Markdown conversion, this Skill supports raw HTML output options, allowing flexible content retrieval based on your specific parsing requirements.

What are the limitations of using a Model Context Protocol server for web scraping?▼

Limitations include strict adherence to robots.txt directives for model-initiated requests, which may block access to restricted pages. Additionally, converting complex HTML to Markdown might lose intricate styling or structural details present in the original web content.