perplexity-search

Perform real-time web-grounded literature searches with source citations via OpenRouter.

48|6|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill perplexity-search-qinyan-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/qinyan-ai/qinyan-academic-skills/tree/main/skills/01-%E8%AE%BA%E6%96%87%E6%A3%80%E7%B4%A2%E4%B8%8E%E6%96%87%E7%8C%AE%E7%AE%A1%E7%90%86/perplexity-search
Command: npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill perplexity-search-qinyan-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Researchers need up-to-date, web-grounded search results with reliable source citations beyond model knowledge cutoff.

Core Features & Use Cases

  • Real-time web search across sources via Perplexity models accessed through OpenRouter.
  • Automatically includes source citations to support findings, enabling literature reviews and quick fact-checks.
  • Simple integration into research pipelines and cross-domain queries (biomedical, computational, clinical) with model switching capabilities.

Quick Start

Configure OPENROUTER_API_KEY and run perplexity_search.py with your query.

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 for a literature review?

Real-time web search with citations is achieved by querying Perplexity models via OpenRouter. The script returns grounded search results and automatically includes source citations to support literature reviews and fact-checking.

What do I need to configure before running real-time web searches with Perplexity?

You need a single OpenRouter API key to run real-time web searches with Perplexity. The script operates through this key using LiteLLM, requiring no additional complex setup to access multiple models for cross-domain queries.

Can I use LiteLLM to switch between different Perplexity models for fact-checking?

Yes, you can switch between multiple Perplexity models using LiteLLM. This model switching capability allows you to adapt your fact-checking and comparative analysis queries across different biomedical and computational science topics.

Does this web search approach include token usage and error handling for research pipelines?

Yes, the web search approach includes token usage tracking and robust error handling. This ensures reliable integration into research pipelines when conducting literature searches or verifying current developments across clinical and computational domains.

What is the best way to find up-to-date developments beyond a model's knowledge cutoff?

The best way to find up-to-date developments beyond a model knowledge cutoff is using web-grounded search via Perplexity. It provides real-time results with source citations, ensuring current information for comparative analyses and literature reviews.