parallel-web

Search the web, extract URL content, and run deep research via the Parallel Chat and Extract APIs.

Updated Jun 18, 2026
One-click install
npx skills add https://github.com/svpfahad/RES200 --skill parallel-web-svpfahad
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-web
Source: https://github.com/svpfahad/RES200/tree/main/claude-scientific-writer-main/.claude/skills/parallel-web
Command: npx skills add https://github.com/svpfahad/RES200 --skill parallel-web-svpfahad

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, parallel-web, and includes scripts (resource) and references (resource) components.

What problem does it solve? Gathering current web information, verifying citations, and producing multi-source research reports normally requires manual searching and reading; this Skill automates web search, URL extraction, and deep research through the Parallel Web Systems APIs with cited, synthesized results. ## Core Features & Use Cases - Web Search: Query the Parallel Chat API (base model) to get synthesized summaries with inline citations for current events, market data, and technical lookups. - Deep Research: Run comprehensive multi-source research reports via the core model, with model selection guidance for depth versus latency tradeoffs. - URL Extraction: Extract clean markdown content from specific URLs for citation verification and DOI resolution. - Use Case: While writing a market analysis section, run a deep research query on the global EV battery market, save the cited report to the sources folder, then verify a specific statistic by extracting content from its source URL. ## Quick Start Ask the assistant to search the web for the latest advances in quantum computing and save the cited results to the sources folder.

Frequently Asked Questions about parallel-web

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

FAQPage Schema
How do I run a web search with the Parallel Chat API?

Run python scripts/parallel_web.py search followed by your natural language query, optionally adding --model core for deeper results and -o to save output to a file. The command returns a synthesized summary with inline citations and a sources list.

What is the difference between the base and core models in Parallel research?

The base model handles standard research and factual queries with 15-100 second latency, while the core model performs complex multi-source synthesis taking 60 seconds to 5 minutes. Use base for quick searches and core for comprehensive deep research reports.

When should I use the Extract API instead of search?

Use the Extract API only when you already have a specific URL, such as verifying a citation's content or reading a known documentation page. For finding information broadly, use the search or research commands instead.

Why does the script fail with PARALLEL_API_KEY not set?

The script requires the PARALLEL_API_KEY environment variable to authenticate with Parallel's APIs. Export it with your key from platform.parallel.ai, and ensure the openai package is installed for search and research commands.

Can I use this for academic paper searches on PubMed or Google Scholar?

This skill is not intended for academic database searches; those route to the research-lookup or citation-management skills. Use parallel-web for general web research, market data, current events, and citation verification via URL extraction.