skills.rest
mrclrchtr
mrclrchtrCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

web-fetch-to-markdown

Fetch HTTP(S) webpages and normalize content into clean Markdown.

54|3|Updated Apr 13, 2026
Search Tags:#markdown#html#readability#llm#scraping#web#content-extraction
One-click install
npx skills add https://github.com/mrclrchtr/SuPi --skill web-fetch-to-markdown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-fetch-to-markdown
Source: https://github.com/mrclrchtr/SuPi/tree/main/.agents/skills/web-fetch-to-markdown
Command: npx skills add https://github.com/mrclrchtr/SuPi --skill web-fetch-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Fetch and normalize HTTP(S) web pages into clean, LLM-friendly Markdown so models and pipelines can summarize, quote, diff, or archive content without the clutter and noise of raw HTML.

Core Features & Use Cases

  • Single-URL fetch and normalization: Retrieve one http or https page and convert its main content into readable Markdown.
  • Flexible output: Write cleaned Markdown to stdout or save to a file with a provided script.
  • Configurable behavior: Support for timeout control, debug mode, and optional absolute link normalization to preserve link integrity.
  • Guardrails: Validates URLs, refuses non-http(s) inputs, and halts when encountering access-controlled or paywalled content.
  • Use Case: Convert a public API doc, blog post, or product page into Markdown for summarization, quoting exact passages, or archiving.

Quick Start

Ask the agent to fetch the URL https://example.com and save the cleaned Markdown output as page.md.

Frequently Asked Questions about web-fetch-to-markdown

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

FAQPage Schema
How do I convert web pages to Markdown for LLM ingestion?▼

To convert web pages to Markdown for LLM ingestion, fetch a single HTTP(S) URL and the tool normalizes the HTML content into clean Markdown. This removes clutter so models can summarize, quote, diff, or archive the text.

What is the best way to extract main content from a URL into Markdown?▼

The best way to extract main content from a URL is to use a scraping tool that validates HTTP(S) inputs and applies readability normalization. It outputs cleaned Markdown to stdout or a file for further use.

Can I normalize absolute links when scraping HTML to Markdown?▼

Yes, you can normalize absolute links when scraping HTML to Markdown. The tool supports optional absolute link normalization to preserve link integrity during the content extraction process.

Does web scraping to Markdown work on paywalled or access-controlled pages?▼

Web scraping to Markdown does not work on paywalled or access-controlled pages. The tool halts processing and refuses non-HTTP(S) inputs when encountering access restrictions to ensure valid content extraction.

How do I save fetched web content as a Markdown file?▼

To save fetched web content as a Markdown file, use the bundled script to write the cleaned output directly to a file. You can also output to stdout or configure timeouts and debug mode as needed.

Related Skills

Explore More Content & Communication Skills→
somnia-chainsomnia-chain
2

somnia-agents-llm-parse-website

Extract structured string or numeric fields from live webpages via markdown conversion.

Official
Advanced
carlos-algmscarlos-algms
2

defuddle

Extract readable main content from web pages as markdown via Defuddle CLI.

Community
Basic
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
venhdevvenhdev

url-to-markdown

Convert public web page URLs into clean Markdown files.

Community
Intermediate