storm-research

Orchestrate multi-perspective literature reviews with citations using the STORM pipeline.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/SamyakJhaveri/loam --skill storm-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: storm-research
Source: https://github.com/SamyakJhaveri/loam/tree/main/cultivation/marketplace/storm-research/skills/storm-research
Command: npx skills add https://github.com/SamyakJhaveri/loam --skill storm-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

STORM provides an end-to-end LLM-powered research pipeline that generates Wikipedia-quality articles with citations, enabling rigorous, structured outputs from diverse perspectives.

Core Features & Use Cases

  • Multi-perspective literature review: systematic exploration from multiple angles with citations.
  • Co-STORM collaboration: supports collaborative direction setting and refinements between researchers and the model.
  • Python package workflow: easy integration into Python projects with minimal boilerplate to generate article-ready content.
  • Use Case: draft a well-cited encyclopedia-quality article on a topic by running STORM to outline sections, sources, and a draft article.

Quick Start

Install knowledge-storm and run STORM with your topic.

Frequently Asked Questions about storm-research

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

FAQPage Schema
How do I generate Wikipedia-quality articles with citations using LLMs?

You can generate cited articles by running the STORM pipeline, which orchestrates multi-perspective literature reviews to outline sections, gather sources, and draft structured Wikipedia-quality outputs end-to-end.

What is multi-perspective literature review and how does it work?

Multi-perspective literature review systematically explores a topic from diverse angles using LLMs. The STORM pipeline simulates researchers collaborating to synthesize structured, cited outputs for systematic reviews and article drafting.

Do I need Python and API keys to run the STORM research pipeline?

Yes, running the STORM pipeline requires Python 3.x, dspy, litellm, and streamlit. You must configure two API keys: one for the LLM and another for the search engine to gather cited sources.

What's the best way to draft a systematic review using Python and LLMs?

The best way to draft a systematic review is using the Co-STORM collaboration workflow in Python, which supports collaborative direction setting and refinements between researchers and the model to generate article-ready content.

Can I integrate the STORM pipeline directly into my Python project?

Yes, you can integrate STORM into Python projects with minimal boilerplate using the knowledge-storm package. It provides a straightforward workflow to generate structured, encyclopedia-quality article drafts programmatically.

When should I not use an automated LLM research pipeline for article drafting?

You should avoid using automated LLM research pipelines when your topic requires highly specialized, non-indexed proprietary data, as the STORM pipeline relies on search engine APIs to gather publicly accessible cited sources for its outputs.