skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

web-search

Search the web and extract page content via Tavily and Exa APIs.

Updated Jul 28, 2026
Search Tags:#research#cli#rag#web search#content extraction#exa#tavily
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill web-search-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/web-search
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill web-search-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It gives AI agents and scripts access to live web search and page content extraction without building custom scrapers or managing search infrastructure. ## Core Features & Use Cases - AI-Powered Search: Run queries through Tavily Search Assistant or Exa Search to get relevant links, answers, and sources. - Content Extraction: Pull clean text and images from URLs using Tavily Extract or Exa Extract. - Direct Answers: Get factual answers to questions via Exa Answer. - Use Case: Build a research agent that searches for the latest developments on a topic, extracts article content, and feeds the results into an LLM for summarization in a RAG pipeline. ## Quick Start Ask the agent to search the web for the latest AI developments using the Tavily search assistant and summarize the top findings.

Frequently Asked Questions about web-search

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

FAQPage Schema
How do I search the web from the command line with Tavily?▼

Run belt app run tavily/search-assistant with a JSON input containing your query. The command returns AI-generated answers with sources and images after you log in with belt login.

What is the difference between Tavily and Exa search?▼

Tavily Search Assistant returns AI-generated answers with sources and images, while Exa Search returns highly relevant links with context. Exa also offers a dedicated Answer app for direct factual responses.

How do I extract text content from a URL?▼

Use belt app run tavily/extract with a JSON input containing a urls array, or exa/extract with a single url field. Both return clean text extracted from the web pages.

Can I combine web search with an LLM for RAG?▼

Yes, pipe search results from Tavily or Exa into an LLM app such as openrouter/claude-sonnet-45 by saving the search output to a file and referencing its content in the LLM prompt.

What do I need to install before using these search apps?▼

You need the inference.sh belt CLI installed and authenticated via belt login. Installation instructions are provided in the inference.sh skills repository.

Related Skills

Explore More Education & Research Skills→
inference-shinference-sh
723

elevenlabs-voice-isolator

Removes background noise and isolates vocals from audio files via the inference.sh CLI.

Official
Basic
shinnytechshinnytech

rag-implementation

Build RAG systems with vector databases and semantic search.

Official
Advanced
lakshya4568lakshya4568

verification

Validates whether generated answers are supported by retrieved evidence or computed values.

Community
Intermediate
ProyectoG007ProyectoG007

Playwright (Automation + MCP + Scraper)

Automate browser interactions and extract data from JavaScript-rendered pages using Playwright.

Community
Advanced