perplexity-search

Performs web searches via Perplexity models with cited source results using LiteLLM and OpenRouter.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/Hung-3008/agusta --skill perplexity-search-hung-3008
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/Hung-3008/agusta/tree/main/.agents/skills/perplexity-search
Command: npx skills add https://github.com/Hung-3008/agusta --skill perplexity-search-hung-3008

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires litellm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Perplexity-search enables AI-powered web searches using Perplexity models via LiteLLM and OpenRouter to fetch current information with grounded source citations.

Core Features & Use Cases

  • Real-time web search across domains using multiple Perplexity models through OpenRouter.
  • Source-cited results for up-to-date literature, clinical findings, and dynamic news.
  • Easy setup and integration with a single API key and a CLI interface for quick queries.

Quick Start

Run a simple search query like 'What are the latest developments in CRISPR research?' and review the grounded, cited results.

Frequently Asked Questions about perplexity-search

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

FAQPage Schema
How do I get real-time web search results with source citations?

Real-time web search with citations is performed using Perplexity models via LiteLLM and OpenRouter to fetch current information and provide grounded source citations across scientific, technical, and general domains.

How do I use Perplexity models through OpenRouter for literature discovery?

Perplexity models are accessed through OpenRouter via LiteLLM to perform literature discovery, allowing you to run queries like 'latest developments in CRISPR research' and review cited, structured results with usage metrics.

Do I need an OpenRouter API key to run AI-powered web searches?

An OpenRouter API key is required to run AI-powered web searches, serving as the single integration point to access Perplexity models and control token limits and verbosity through the CLI interface.

Can I select different Perplexity models and control verbosity for web search queries?

Model selection and token/verbosity controls are supported when running web search queries, returning structured results with usage metrics tailored to your specified parameters and query requirements.

What are the limitations of using LiteLLM for grounded web searches?

LiteLLM web searches depend on a single OpenRouter API key and available Perplexity models, limiting queries to supported domains and the response structure returned by the selected model's real-time retrieval capabilities.