skills.rest
markacianfrani
markacianfraniCOMMUNITY
Explore all skills by this author →
Website𝕏@markacianfraniGitHub

web-fetch

Fetch web pages and convert HTML into markdown, text, or raw HTML.

6|Updated Jan 14, 2026
Search Tags:#automation#markdown#scraping#http#web-fetch#content-extraction
One-click install
npx skills add https://github.com/markacianfrani/armor --skill web-fetch-markacianfrani
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-fetch
Source: https://github.com/markacianfrani/armor/tree/main/skills/web-fetch
Command: npx skills add https://github.com/markacianfrani/armor --skill web-fetch-markacianfrani

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires html-to-text, turndown, and includes scripts (resource) components.

What problem does it solve?

This skill solves the friction of manually browsing, copying, and cleaning web content by programmatically fetching and converting URLs into structured, LLM-ready formats.

Core Features & Use Cases

  • Content Conversion: Automatically transforms raw HTML into clean Markdown or plain text.
  • Smart Fetching: Supports content negotiation to retrieve LLM-optimized markdown directly when available.
  • Use Case: Use this to quickly ingest documentation, articles, or GitHub code blobs into your current context without needing to open a browser or manually clean up web markup.

Quick Start

Ask the assistant to fetch the content of a specific URL and convert it into markdown format for your review.

Frequently Asked Questions about web-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 context?▼

To convert web page HTML to markdown, this skill fetches URLs and automatically sanitizes the markup into structured markdown. It uses content negotiation to retrieve LLM-optimized markdown directly when supported by the source.

Can I extract plain text from a web page without opening a browser?▼

Yes, you can extract plain text from web pages without a browser by fetching the URL directly. The skill processes raw HTML and converts it into clean text or markdown formats for immediate use.

How do I fetch content from a GitHub code blob into markdown?▼

Fetching content from a GitHub code blob into markdown is supported natively. The skill retrieves the raw page content from GitHub URLs and converts the structured markup into LLM-ready markdown or text.

Do I need Node or Bun to run web scraping and content extraction?▼

Yes, you need either Bun or Node installed to run web scraping and content extraction. The skill specifically requires the html-to-text and turndown dependencies to process and sanitize web markup.

What is the best way to automate gathering documentation from multiple URLs?▼

The best way to automate gathering documentation is to programmatically fetch and convert URLs into structured formats. This eliminates manual copying and cleaning by retrieving articles or docs and transforming them into LLM-ready markdown.

Why does fetching web content return raw HTML instead of clean markdown?▼

Fetching web content might return raw HTML if the source site lacks native markdown support. The skill still processes this HTML using html-to-text and turndown to sanitize and convert the markup into structured text or markdown.

Related Skills

Explore More Software Engineering Skills→
samymitysamymity
1

bun-runtime

Migrate Node commands and npm scripts to Bun equivalents.

Community
Intermediate
marktantongcomarktantongco

nvidia-nim-api-builder

Automate LLM inference via NVIDIA NIM API for text generation and summarization.

Community
Advanced
sky770825sky770825

web-fetch

Fetch web content via HTTP requests and convert it to Markdown or plain text.

Community
Basic
zeronx798zeronx798

scrapling

Scrape static, dynamic, and protected websites using the scrapling library.

Community
Advanced