perplexity-search

Perform web searches with Perplexity models via OpenRouter and LiteLLM.

321|26|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/mkurman/tamux --skill perplexity-search-mkurman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/mkurman/tamux/tree/main/skills/scientific-skills/perplexity-search
Command: npx skills add https://github.com/mkurman/tamux --skill perplexity-search-mkurman

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly obtain up-to-date, web-grounded information for scientific and technical inquiries using Perplexity models via OpenRouter and LiteLLM, enabling grounded answers with citations instead of relying on model memory.

Core Features & Use Cases

  • Access multiple Perplexity models (Sonar Pro, Sonar Pro Search, Sonar Reasoning Pro) through a single OpenRouter API key.
  • Retrieve real-time information and literature results with source citations for verification.
  • Simple setup and integration with other scientific-skills workflows for literature review, technical documentation, and hypothesis exploration.

Quick Start

Run a sample search such as asking for the latest clinical trials in CAR-T therapy in 2024.

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-grounded answers with source citations for scientific research?

Perform AI-powered web-grounded searches using Perplexity models through LiteLLM and OpenRouter to obtain real-time results with source citations for scientific research verification. This prevents reliance on static model memory.

Do I need an OpenRouter API key to access Perplexity models for literature searches?

Yes, an OpenRouter API key is required to access multiple Perplexity models like sonar-pro and sonar-reasoning-pro. This single key integration also requires LiteLLM setup to route queries.

Can I use LiteLLM to query Perplexity sonar models for current clinical trial information?

Yes, you can use LiteLLM to query Perplexity sonar models for current clinical trial information. The skill routes domain-specific queries across scientific disciplines via OpenRouter to retrieve real-time data.

What is the best way to retrieve up-to-date technical documentation without relying on model memory?

The best way to retrieve up-to-date technical documentation without relying on model memory is using Perplexity web search via LiteLLM. This approach returns grounded answers with direct source citations for verification.

Which Perplexity models are available through OpenRouter for domain-specific scientific queries?

Available Perplexity models through OpenRouter include sonar-pro, sonar-pro-search, sonar, sonar-reasoning-pro, and sonar-reasoning. These models facilitate domain-specific scientific queries and literature reviews.

Why use Perplexity web search instead of standard LLM queries for hypothesis exploration?

Use Perplexity web search instead of standard LLM queries for hypothesis exploration because it provides real-time, web-grounded results with citations. Standard LLM queries rely on potentially outdated model memory.