exa-search

Search the web and extract content with configurable filters.

2|1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/raja21068/AutoResearch --skill exa-search-raja21068
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exa-search
Source: https://github.com/raja21068/AutoResearch/tree/main/skills/aris/exa-search
Command: npx skills add https://github.com/raja21068/AutoResearch --skill exa-search-raja21068

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

exa-search removes the time-consuming task of manually finding relevant web pages by automatically searching the broader web and extracting usable content from the results.

Core Features & Use Cases

  • Broad Web Search with Extraction: Finds pages beyond academic databases and returns results with extracted highlights, text, or summaries.
  • Academic and Similar-Page Modes: Supports searching for research papers and finding similar pages starting from a URL.
  • Paper-First Ingestion Hook: When research-wiki exists and results are research-paper category, it can ingest metadata into the research wiki automatically.

Quick Start

Ask for web research by running: exa-search "rag pipelines" — max: 5.

Frequently Asked Questions about exa-search

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

FAQPage Schema
How do I extract readable content from web search results for research?

Web search with content extraction retrieves pages matching your query and returns structured results with readable text or highlights. You can filter by category, date, and domain to target specific content types.

Can I find web pages similar to a specific URL?

Yes, similar-page discovery takes a starting URL and searches the broader web for pages with related content. This helps expand literature gathering or product research from a known relevant source.

Do I need an API key to perform AI-powered web search?

Yes, an Exa API key is required to authenticate search requests. The Skill uses this key to query the web, apply filters like research-paper-only mode, and return extracted content.

What's the best way to search for research papers beyond academic databases?

Use the academic and similar-page modes to find research papers across the broader web. You can filter results to research-paper-only categories and automatically ingest metadata into a research wiki.

How does web search with content extraction handle date and domain filters?

You can apply controllable filters for category, date, and domain to narrow results before content extraction. This ensures the returned text or highlights match your specific timeframe and source requirements.

Can I limit the number of search results returned with content extraction?

Yes, you can specify a maximum number of results when running a search query. This controls how many pages are retrieved and have their content extracted, keeping responses focused.