exa
Neural web search and code context via Exa AI API. Requires EXA_API_KEY. Use for finding documentation, code examples, research papers, or company info.
When & Why to Use This Skill
The Exa skill integrates advanced neural web search capabilities into Claude, allowing for high-quality information retrieval that goes beyond traditional keyword matching. By leveraging the Exa AI API, it provides context-aware results for technical documentation, code snippets, research papers, and company data, making it an essential tool for users who require precise and up-to-date web intelligence.
Use Cases
- Technical Documentation & Code Discovery: Quickly locate specific API references, library documentation, and relevant code examples from GitHub to streamline the development workflow.
- Academic and Professional Research: Find peer-reviewed research papers, PDFs, and industry-specific news by utilizing specialized search categories like 'research-paper' or 'company'.
- Deep Content Extraction: Retrieve full-text content from multiple URLs to provide Claude with comprehensive context for summarization, data analysis, or report generation.
- Market Intelligence: Monitor competitor updates, company profiles, and social trends by filtering searches for personal sites, tweets, or news articles.
| name | exa |
|---|---|
| description | Neural web search and code context via Exa AI API. Requires EXA_API_KEY. Use for finding documentation, code examples, research papers, or company info. |
| metadata | {"clawdbot":{"emoji":"🧠","requires":{"env":["EXA_API_KEY"]}}} |
Exa - Neural Web Search
Direct API access to Exa's neural search engine.
Setup
1. Get your API Key: Get a key from Exa Dashboard.
2. Set it in your environment:
export EXA_API_KEY="your-key-here"
Usage
Web Search
bash scripts/search.sh "query" [num_results] [type]
type: auto (default), neural, fast, deepcategory: company, research-paper, news, github, tweet, personal-site, pdf
Code Context
Finds relevant code snippets and documentation.
bash scripts/code.sh "query" [num_results]
Get Content
Extract full text from URLs.
bash scripts/content.sh "url1" "url2"