perplexity

Fetch real-time web search results with citations via the Perplexity API.

1|Updated Nov 12, 2025
One-click install
npx skills add https://github.com/grahama1970/fetcher --skill perplexity-grahama1970
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity
Source: https://github.com/grahama1970/fetcher/tree/main/.agents/skills/perplexity
Command: npx skills add https://github.com/grahama1970/fetcher --skill perplexity-grahama1970

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Real-time access to current information from the web to answer questions that exceed training data.

Core Features & Use Cases

  • Real-time web research with citations for current events, pricing, and technical topics.
  • Easy model selection and a CLI interface to ask questions or perform in-depth research.
  • Automatic handling of API keys from environment or .env files, and structured JSON outputs with usage data.

Quick Start

Run the Perplexity CLI with the ask or research subcommands to fetch answers and citations.

Frequently Asked Questions about perplexity

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

FAQPage Schema
How do I get real-time web search results with citations for current events?

Real-time web search with citations is delivered by fetching fresh sources via the Perplexity API. You can retrieve up-to-date information for current events, pricing, and technical topics using ask or research subcommands.

How do I configure API keys to run a Perplexity CLI client?

Configuring API keys for the Perplexity CLI client requires setting the PERPLEXITY_API_KEY environment variable or placing it in a .env file. The client automatically reads this key to authenticate web search requests.

Does this web search tool provide structured JSON outputs with usage data?

Yes, the web search tool provides structured JSON outputs with usage data. It maps user-friendly model names to API IDs and returns results containing both the requested information and API usage metrics.

What's the best way to verify current information that exceeds model training data?

Verifying current information that exceeds training data is handled by executing real-time web research. The tool fetches fresh sources with optional model sizing, providing cited answers for technical questions and fact-checking.

Can I select different model sizes for in-depth web research queries?

Yes, you can select different model sizes for web research queries. The CLI interface supports optional model sizing by mapping user-friendly model names to specific API IDs when constructing messages for in-depth research.