perplexity-research

Retrieve external information via Perplexity MCP search models.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/Wangmengguo/opencode-skills --skill perplexity-research-wangmengguo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-research
Source: https://github.com/Wangmengguo/opencode-skills/tree/main/perplexity-research
Command: npx skills add https://github.com/Wangmengguo/opencode-skills --skill perplexity-research-wangmengguo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps retrieve and verify external information, ensuring a stable, traceable, and controllable external referral process using Perplexity MCP.

Core Features & Use Cases

  • External Information Retrieval: Utilizes Perplexity MCP for searching, fact-checking, and comparison of information.
  • Priority-Based Search: Prioritizes perplexity_search for quick results, with perplexity_research as a fallback for more in-depth information.
  • Model Selection: Offers different Perplexity models like sonar, sonar-pro, and sonar-reasoning for varying search needs.
  • Process SOP: Defines a standard operating procedure for triggering the skill, handling sensitive information, and ensuring output quality.

Quick Start

To initiate a search, use the command: ~/.config/opencode/scripts/perplexity-search.sh "your question"

Frequently Asked Questions about perplexity-research

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

FAQPage Schema
How do I access external information for fact-checking within OpenCode?

To access external information for fact-checking, you can run the Perplexity search script via the command line interface. This skill utilizes Perplexity MCP to retrieve stable and traceable external data directly within your workflow.

What is the best way to retrieve latest news and comparative data using Perplexity MCP?

The best way to retrieve latest news and comparative data is by prioritizing the perplexity_search function for quick results. If you need more in-depth information, the skill automatically falls back to perplexity_research.

Can I select different Perplexity models for varying search depths?

Yes, you can select different Perplexity models for varying search depths. The skill supports multiple models including sonar, sonar-pro, and sonar-reasoning to handle different information retrieval needs.

Does this external information retrieval process handle sensitive information safely?

Yes, the external information retrieval process handles sensitive information safely. It defines a standard operating procedure that controls external referrals and ensures output quality while maintaining traceability.

How do I trigger a Perplexity search from the command line?

To trigger a Perplexity search from the command line, execute the script using the command format `~/.config/opencode/scripts/perplexity-search.sh "your question"`. This initiates the search with your specified query.

Why does the skill prioritize quick search results over in-depth research?

The skill prioritizes quick search results over in-depth research to optimize retrieval speed and efficiency. It uses perplexity_search first for rapid facts, only escalating to perplexity_research when deeper comparative data is required.