skills.rest
nielpattin
nielpattinCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

visit-webpage

Retrieve web page content, converting HTML to markdown or downloading images.

Updated Apr 21, 2026
Search Tags:#markdown#web scraping#content extraction#image download#jina reader#webpage reader
One-click install
npx skills add https://github.com/nielpattin/.dotfiles --skill visit-webpage
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visit-webpage
Source: https://github.com/nielpattin/.dotfiles/tree/main/.pi/agent/skills/visit-webpage
Command: npx skills add https://github.com/nielpattin/.dotfiles --skill visit-webpage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of retrieving and processing content from web pages, whether it's readable text or image files, saving you the manual effort of browsing and downloading.

Core Features & Use Cases

  • Extracts Web Content: Fetches articles, documentation, and other HTML content, converting it into markdown format.
  • Downloads Images: Automatically detects and downloads image files from URLs.
  • Handles JavaScript: Uses Jina Reader to process dynamically rendered web pages.
  • Use Case: Quickly get the key information from a long online article without reading through ads and sidebars, or download a specific image directly from a webpage.

Quick Start

Use the visit-webpage skill to get the markdown content from the url https://example.com/article.

Frequently Asked Questions about visit-webpage

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

FAQPage Schema
How do I convert web page HTML to markdown for content extraction?▼

You can convert web page HTML to markdown by fetching the target URL; the Skill processes articles and documentation, transforming raw HTML into clean markdown content for data scraping and summarization.

Does web scraping work on JavaScript-rendered web pages?▼

Web scraping works on JavaScript-rendered web pages by using Jina Reader to process dynamically loaded content, ensuring you extract the fully rendered text rather than just the static HTML source.

Can I download images directly from a webpage URL?▼

Yes, you can download images directly from a webpage URL. The Skill automatically detects and retrieves image files from URLs, handling various image formats for asset collection.

What is the best way to get key information from a long online article without ads?▼

The best way to get key information without ads is to extract the web content into markdown format. This fetches the article text while filtering out sidebars and advertisements for clean summarization.

What are the limitations of using Jina Reader for web content extraction?▼

While Jina Reader handles JavaScript-rendered content effectively, web content extraction depends on the target website's accessibility and structure. Complex layouts may still produce fragmented markdown text.

Related Skills

Explore More Content & Communication Skills→
aryaniyapsaryaniyaps
26

firecrawl-build-scrape

Extract HTML, markdown, links, and screenshots from known URLs.

Community
Intermediate
42atom42atom

twitter-media

Extract tweet text, author, and media from Twitter/X URLs via fxTwitter API.

Community
Intermediate
El3tar-cmdEl3tar-cmd
18

photo-editor

Edit, resize, crop, filter, and optimize images with Pillow or sharp.

Community
Intermediate
mjunaidcamjunaidca
2

browser-use

Automate browser interactions for navigation, form submission, and web scraping.

Community
Advanced