Skill Detail

Run autonomous deep research workflows with GPT Researcher

Use GPT Researcher to plan, gather, source, and assemble cited web or local research reports through a repeatable agent workflow.

Research & ScrapingMulti-Framework
Research & Scraping Multi-Framework Security Reviewed
⭐ 27.4k GitHub stars ⬇ 1.6k/wk npm
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill run-autonomous-deep-research-workflows-with-gpt-researcher Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python 3.11+, GPT Researcher, LLM provider API key, Tavily or configured retriever
Install & setup
Install with `pip install gpt-researcher`, configure provider and retriever API keys such as `OPENAI_API_KEY` and `TAVILY_API_KEY`, then run GPT Researcher from the package, app, Docker setup, or Claude Skill path documented upstream.
Author
assafelovic
Publisher
Individual
Last updated
May 29, 2026
Quick brief

Use GPT Researcher when an agent needs to turn a research question into a cited report instead of manually searching, opening tabs, and stitching notes together. The workflow plans subquestions, gathers web or local context, summarizes sources, and assembles a long-form report with citations. The boundary is deep research execution and report generation, not a generic search tool, browser scraper, or broad LLM application framework.

How it works

What this skill actually does

Inputs and prerequisites: Python 3.11+, GPT Researcher, LLM provider API key, Tavily or configured retriever.

Setup notes: Install with `pip install gpt-researcher`, configure provider and retriever API keys such as `OPENAI_API_KEY` and `TAVILY_API_KEY`, then run GPT Researcher from the package, app, Docker setup, or Claude Skill path documented upstream.

Source and verification boundary: use https://docs.gptr.dev as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.