gpt-researcher

Automate deep web research for academic context and policy documents.

21|4|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/HaipingXu/social-science-claude-scholar --skill gpt-researcher-haipingxu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gpt-researcher
Source: https://github.com/HaipingXu/social-science-claude-scholar/tree/main/skills/gpt-researcher
Command: npx skills add https://github.com/HaipingXu/social-science-claude-scholar --skill gpt-researcher-haipingxu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gpt-researcher, langchain-anthropic, langchain-huggingface, sentence-transformers, tavily-python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of gathering background context, policy documents, grey literature, and institutional history from the web, which is crucial for academic research but time-consuming to do manually.

Core Features & Use Cases

  • Autonomous Web Research: Conducts deep research on a given topic using web search and synthesis.
  • Grey Literature & Policy Documents: Specifically designed to find non-academic sources like government reports and think tank papers.
  • Local Document Integration: Can also research across a corpus of local PDF documents (RAG).
  • Use Case: A political science PhD student needs to understand the historical policy context of a specific country's economic reforms. This Skill can autonomously gather relevant government reports, news archives, and policy documents to build a comprehensive background section for their paper.

Quick Start

Use the gpt-researcher skill to research the political economy of state-business relations in Taiwan from 1949-1980.

Frequently Asked Questions about gpt-researcher

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

FAQPage Schema
How do I automate web research for academic writing and grey literature?

Automate web research for academic writing by using LLMs and search engines to autonomously gather background context, policy history, and grey literature. This synthesizes non-academic sources like government reports into comprehensive background sections.

What is the best way to find policy documents and institutional history for a research paper?

The best way to find policy documents is using autonomous web research tools that deep search the web for grey literature and institutional history. This specifically targets government reports and think tank papers to build historical context.

Can I analyze local PDF documents alongside autonomous web search results?

Yes, you can analyze local PDF documents alongside web search results. The tool supports hybrid search modes, allowing you to research across a local PDF corpus using RAG while simultaneously gathering online background context.

Do I need API keys to use LLM providers and search engines like Tavily for background research?

Yes, you need API keys for LLM providers and search engines like Tavily to conduct autonomous background research. These keys are required to access the language models and web search mechanisms that power the deep research synthesis.

How does autonomous web research handle non-academic sources like government reports?

Autonomous web research handles non-academic sources by specifically targeting grey literature and policy documents. It uses LLMs to synthesize government reports, news archives, and think tank papers into structured academic context.

When should I use hybrid search modes instead of autonomous web research for academic context?

Use hybrid search modes instead of autonomous web research when you need to integrate an existing local PDF corpus with new online findings. This combines local RAG analysis with web search to build comprehensive academic background context.