llm-reader

🥇Gold

llm-reader transforms webpages into LLM-friendly text, streamlining data extraction for AI applications. Ideal for RAG and web scraping, it simplifies the process of extracting images and links, enhancing your AI capabilities.

286190Updated Today

Intermediate15 minutes to implementai-agents

Saves ~480 min per use

Quick InstallView Source

claude install m92vyas/llm-reader

Works with:

ChatGPTClaude

Overview

About This Skill

How to Use

["1. Identify the webpage URL you want to process. Ensure it is accessible and contains the information you need.","2. Use the llm-reader tool to extract the main content, images, and links from the webpage. Specify the type of content you are interested in, such as product features or pricing details.","3. Review the extracted content to ensure it meets your requirements. Use the structured text for further LLM processing, such as summarization or sentiment analysis.","4. Integrate the extracted data into your AI applications, such as a RAG pipeline or web scraping project, to enhance your AI capabilities.","5. For better results, ensure the webpage is well-structured and contains the specific content you are looking for. Use the extracted data to create interactive dashboards or reports in tools like Mode."]

Use Cases

Extracting text from product pages for analysis

Gathering data from competitor websites

Automating content generation from web sources

Scraping images for training AI models

Best For

MarketingGrowth

Setup & Installation

Quick Install

Terminal

claude install m92vyas/llm-reader

Alternative Install (Git Clone)

git clone https://github.com/m92vyas/llm-reader

Requirements

Claude Code or compatible AI agent
Works with: ChatGPT, Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use llm-reader to extract the main content from the webpage [URL]. Identify and list all images and links found on the page. Format the output as structured text suitable for LLM processing. Focus on extracting [SPECIFIC_CONTENT_TYPE] such as product features, pricing details, or customer testimonials.

Example Output

After processing the webpage [URL] with llm-reader, the extracted content is as follows:

Main Content:
ThoughtSpot has acquired Mode, a collaborative analytics platform, for $200 million. This acquisition aims to redefine the next generation of business intelligence (BI) by combining ThoughtSpot's search-driven analytics with Mode's interactive dashboards and SQL-based data exploration. The integration will enhance collaborative analytics, enabling teams to explore, analyze, and share insights more effectively.

Images:
1. ThoughtSpot and Mode logos side by side
2. Interactive dashboard screenshot
3. Team collaboration illustration

Links:
1. [Learn More about the acquisition](https://www.thoughtspot.com/press-releases/thoughtspot-completes-200m-acquisition-of-mode-analytics)
2. [Try Mode for free](https://www.thoughtspot.com/mode-free-trial)
3. [Contact Sales](https://www.thoughtspot.com/contact-sales)

The extracted content is now structured and ready for further LLM processing, such as summarization, sentiment analysis, or integration into a RAG pipeline.