web-article-collector

Extract article content from public webpages and save Markdown notes.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lordking/lee-second-brain-os --skill web-article-collector
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-article-collector
Source: https://github.com/lordking/lee-second-brain-os/tree/main/skills/kb-web-page-collecting
Command: npx skills add https://github.com/lordking/lee-second-brain-os --skill web-article-collector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This capability automates capturing content from public web pages, extracting the article body, and generating a clean Markdown note with an AI-generated summary, saving time and ensuring consistent formatting.

Core Features & Use Cases

  • Content extraction from public webpages (article/main content)
  • AI-assisted summarization to produce concise notes
  • Markdown output ready for knowledge bases or personal archives
  • Use Case: Save blog posts, tutorials, or technical documents and browse later with context

Quick Start

Provide a public URL to fetch, extract the article, and save a summarized Markdown note.

Frequently Asked Questions about web-article-collector

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

FAQPage Schema
How do I extract web articles and save them as Markdown notes?

To extract web articles and save them as Markdown notes, provide a public URL to the tool. It validates the link, extracts the main HTML content, and formats the text into a clean Markdown file for your knowledge base.

What is the best way to summarize web pages for a personal knowledge base?

The best way to summarize web pages for a knowledge base is using an automated extraction tool that fetches the article body and applies AI summarization. This generates concise Markdown notes with context for later reference.

How does AI summarization work for clipped web articles?

AI summarization for clipped web articles works by first extracting the main content from the public webpage HTML, then processing the text to generate a concise summary. The output is formatted as a Markdown note ready for archiving.

Can I use this to collect content from any public webpage?

You can use this to collect content from public webpages, but it requires URL validation and relies on HTML content extraction. It includes safe defaults and error handling to manage inaccessible pages or extraction failures.

What are the limitations of automated web article extraction?

Limitations of automated web article extraction include dependence on URL validation and the target page's HTML structure. It operates only on public webpages, so restricted or dynamically rendered content may trigger error handling instead of successful extraction.