web-researcher

Search, extract, and synthesize information from web, academic, and patent sources.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/milo0914/hermes-skills-backup --skill web-researcher-milo0914
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-researcher
Source: https://github.com/milo0914/hermes-skills-backup/tree/main/web-researcher
Command: npx skills add https://github.com/milo0914/hermes-skills-backup --skill web-researcher-milo0914

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, curl, and includes references (resource) components.

What problem does it solve?

This skill solves the challenge of fragmented information gathering by automating the search, extraction, and synthesis of data from multiple web sources, including academic databases and patent repositories.

Core Features & Use Cases

  • Multi-Source Synthesis: Aggregates information from real-time search, academic papers, and patent databases into structured reports.
  • Advanced Patent Analysis: Uses browser automation to navigate JavaScript-heavy patent databases like Google Patents and WIPO.
  • Academic Research: Directly fetches and summarizes papers from arXiv.org.
  • Use Case: Use this to perform a competitive market analysis or a technical prior-art search that requires cross-referencing multiple live sources.

Quick Start

Ask the web researcher to find and summarize the latest developments on a specific technology topic including relevant patent and academic sources.

Frequently Asked Questions about web-researcher

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

FAQPage Schema
How do I automate web research and synthesize information from multiple online sources?▼

Automate multi-source web research by using browser automation to search, extract, and synthesize information from diverse online sources into structured reports. It aggregates data from real-time search, academic databases, and patent repositories.

Can I extract data from JavaScript-rendered patent databases like Google Patents and WIPO?▼

Yes, you can extract data from JavaScript-rendered patent databases like Google Patents and WIPO. The skill uses Playwright browser automation to navigate dynamic web content and handle JavaScript-heavy pages for advanced patent analysis.

What is the best way to perform a technical prior-art search across academic papers and patents?▼

The best way to perform a prior-art search is cross-referencing live sources. This approach directly fetches and summarizes papers from arXiv.org while using browser automation to navigate patent databases for comprehensive analysis.

Do I need Playwright and curl to handle dynamic web content extraction?▼

Yes, you need Playwright and curl to handle dynamic web content extraction. These dependencies allow the system to integrate with search APIs and perform browser automation required for scraping JavaScript-rendered pages.

How does literature review automation work for fetching academic papers from arXiv?▼

Literature review automation works by directly fetching and summarizing academic papers from arXiv.org. It aggregates extracted summaries alongside real-time search and patent data into a structured, comprehensive report.