skills.rest
inference-sh
inference-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

web-search

Search the web and extract content using Tavily and Exa APIs.

688|95|Updated Jan 31, 2026
Search Tags:#research#AI agent#information retrieval#web search#content extraction#Exa#Tavily
One-click install
npx skills add https://github.com/inference-sh/skills --skill web-search-inference-sh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/inference-sh/skills/tree/main/tools/llm/web-search
Command: npx skills add https://github.com/inference-sh/skills --skill web-search-inference-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates web searching and content extraction, providing quick access to information and reducing the need for manual browsing and data collection.

Core Features & Use Cases

  • Web Search: Perform AI-powered searches using services like Tavily and Exa.
  • Content Extraction: Extract text and images from specified URLs.
  • Direct Answers: Get factual answers to questions directly.
  • Use Case: A product manager needs to research competitor features. They can use this Skill to search for relevant articles, extract key information, and get concise answers, all without leaving their workflow.

Quick Start

Use the web-search skill to find the latest AI developments in 2024.

Frequently Asked Questions about web-search

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

FAQPage Schema
How do I automate web search and content extraction for an AI agent?▼

Automated web search and content extraction is enabled through Tavily and Exa APIs, allowing AI agents to perform information retrieval and text aggregation without manual browsing.

What is the best way to extract text and images from specific URLs for research?▼

URL content extraction pulls text and images directly from specified web pages, reducing manual data collection and streamlining research pipelines.

Can I use this for fact-checking and getting direct answers to questions?▼

Fact-checking is supported by retrieving direct, factual answers to questions using the integrated search APIs to verify information accuracy.

Does this web search skill support building RAG pipelines?▼

RAG pipelines are fully supported, facilitating automated information retrieval and content aggregation to feed downstream analysis and generation.

How do I research competitor features without leaving my product management workflow?▼

Researching competitor features involves searching relevant articles, extracting key information, and getting concise answers directly within your existing workflow.

Do I need Tavily or Exa APIs to perform AI-powered searches?▼

Tavily and Exa APIs are required to perform AI-powered web searches and extract content, serving as the core mechanism for information retrieval.

Related Skills

Explore More Product & Management Skills→
SheshiyerSheshiyer
4

infsh-web-search

Search the web and extract content using Tavily or Exa via inference.sh.

Community
Intermediate
48Nauts-Operator48Nauts-Operator
3

rag-implementation

Build Retrieval-Augmented Generation systems with vector databases and semantic search.

Community
Advanced
ai-kitchen-incai-kitchen-inc
2

data-layer

Chunk documents, generate embeddings, and index vectors in Pinecone for RAG.

Community
Intermediate
twjarviszyra-webtwjarviszyra-web
3

scrapling

Extract web content from static, dynamic, and protected pages via Scrapling APIs.

Community
Advanced