
Perplexity Search
This is a straightforward wrapper around Perplexity's search models via OpenRouter, so you can get real-time web results with citations without leaving your Claude workflow. You'd reach for it when you need current information beyond the training cutoff, like recent papers, technical updates, or fact-checking with sources. It supports multiple Perplexity models (sonar-pro for general use, sonar-pro-search for complex queries, sonar-reasoning-pro when you need explicit step-by-step analysis). The setup is simple if you already have an OpenRouter key, and the documentation actually shows you how to craft better queries instead of just listing API parameters. Main thing to know is this costs money per query through OpenRouter, so it's not for casual browsing.
- skills.sh installs
- 674
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill perplexity-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Perplexity Search
Overview
Perform AI-powered web searches using Perplexity models through LiteLLM and OpenRouter. Perplexity provides real-time, web-grounded answers with source citations, making it ideal for finding current information, recent scientific literature, and facts beyond the model's training data cutoff.
This skill provides access to all Perplexity models through OpenRouter, requiring only a single API key (no separate Perplexity account needed).
When to Use This Skill
Use this skill when:
- Searching for current information or recent developments (2024 and beyond)
- Finding latest scientific publications and research
- Getting real-time answers grounded in web sources
- Verifying facts with source citations
- Conducting literature searches across multiple domains
- Accessing information beyond the model's knowledge cutoff
- Performing domain-specific research (biomedical, technical, clinical)
- Comparing current approaches or technologies
Do not use for:
- Simple calculations or logic problems (use directly)
- Tasks requiring code execution (use standard tools)
- Questions well within the model's training data (unless verification needed)
Sponsors
Details
- Repository
- github.com/davila7/claude-code-templates
- Categories
- Backend & APIs, AI & Agent Building
- First seen
- May 16, 2026
More from davila7/claude-code-templates
All 618- Nestjs Expert672
- Scroll Experience669
- Pytorch Lightning645
- Frontend Patterns638
- Agent Evaluation637
- Nextjs Best Practices632
- Gdpr Dsgvo Expert627
- Peer Review612
- Prompt Engineering604
- Web Design Guidelines603
- Cto Advisor595
- Latex Posters592
- Context Window Management587
- Humanizer585
- Product Manager Toolkit585
- Agent Memory Mcp575
- I18n Localization570
- Audiocraft Audio Generation569
- Agent Manager Skill568
- Research Lookup567
- Seaborn565
- Tailwind Patterns564
- Brainstorming562
- Feature Design Assistant559