perplexity-search

Automate real-time web searches with cited sources via Perplexity models.

1|2|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/fuzzy-dynamics/strings --skill perplexity-search-fuzzy-dynamics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/perplexity-search
Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill perplexity-search-fuzzy-dynamics

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly obtaining up-to-date, web-grounded information with reliable source citations, eliminating reliance on static model knowledge.

Core Features & Use Cases

  • Real-time web search across multiple Perplexity models (sonar-pro, sonar-pro-search, sonar-reasoning) via a unified API key.
  • Web-grounded answers with cited sources suitable for literature discovery, technical research, and domain-specific inquiries.
  • Easy integration with existing research pipelines and scripts for reproducible results.

Quick Start

Ask it to search for the latest scientific developments on a given topic and return grounded results with citations.

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 grounded citations for literature discovery?

Real-time web search with grounded citations is automated by querying multiple Perplexity models via OpenRouter to retrieve up-to-date, source-cited information for literature discovery and technical research.

Do I need an OpenRouter API key to use Perplexity models for web-grounded research?

Yes, an OpenRouter API key is required to access Perplexity models like sonar-pro and sonar-reasoning for retrieving web-grounded answers with cited sources.

Can I configure max_tokens and temperature when using LiteLLM for real-time web searches?

LiteLLM supports configurable max_tokens and temperature settings when routing requests through the OpenRouter Perplexity namespace for real-time web search and cross-domain research.

What is the best way to integrate web-grounded answers with cited sources into existing research pipelines?

Integrating web-grounded answers into existing research pipelines is achieved by using the provided scripts to automate Perplexity API calls, ensuring reproducible results with reliable source citations.

Does this approach eliminate reliance on static model knowledge for up-to-date information retrieval?

Yes, obtaining up-to-date information with reliable source citations eliminates reliance on static model knowledge by automating real-time web searches across multiple Perplexity models.

What Perplexity models are available via the OpenRouter namespace for domain-specific inquiries?

Multiple Perplexity models including sonar-pro, sonar-pro-search, and sonar-reasoning are available via the OpenRouter namespace to provide web-grounded answers for domain-specific inquiries.