llm-context

What problem does it solve?

This Skill provides pre-extracted, relevance-ranked web content optimized for grounding LLM responses, enabling AI agents to reason directly over real-time search results without needing to parse raw HTML.

Core Features & Use Cases

• Direct Content Extraction: Retrieves text, tables, and code blocks directly from web pages, bypassing the need for LLMs to scrape and parse HTML.
• Optimized for LLMs: Content is pre-processed and structured for efficient ingestion by AI models.
• RAG & AI Agents: Ideal for building Retrieval Augmented Generation pipelines and empowering AI agents with up-to-date information.
• Custom Ranking with Goggles: Allows fine-grained control over data sources used for grounding.

Quick Start

Use the llm-context skill to get pre-extracted web content for the query "tallest mountains in the world".