Skills
.Work. You
Rest

WebExtract

Community

Extracts clean text from web pages.

Content & Communication#web scraping#content extraction#text retrieval#web page parsing#llm input
AuthorDaveSteadman
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the process of fetching web page content and stripping away all non-essential elements like HTML markup, navigation, scripts, and advertisements, providing only the clean, readable prose.

Core Features & Use Cases

  • Web Page Content Extraction: Fetches content from any HTTP/HTTPS URL.
  • Noise Reduction: Strips HTML, navigation, ads, and scripts to isolate core text.
  • LLM-Ready Output: Returns clean text suitable for summarization or synthesis by an LLM.
  • Use Case: When researching a topic, you can use this skill to quickly get the main points from a relevant article without being distracted by website design or ads.

Quick Start

Fetch the page at https://example.com/article and extract up to 400 words of its text.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: WebExtract
Download link: https://github.com/DaveSteadman/MiniAgentFramework/archive/main.zip#webextract

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.