deep-research

Name: deep-research
Availability: InStock
Author: moonlight-lupin

Automate multi-step research and generate cited reports for broad topics.

15|3|Updated Jul 8, 2026

Search Tags:#report generation #information synthesis #deep research #multi-source synthesis #cited reports

Ready to run

npx skills add https://github.com/moonlight-lupin/agent-skills --skill deep-research-moonlight-lupin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/moonlight-lupin/agent-skills/tree/main/research/deep-research
Command: npx skills add https://github.com/moonlight-lupin/agent-skills --skill deep-research-moonlight-lupin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires web_search, web_extract, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of in-depth research and generating high-quality, cited reports, saving time and ensuring accuracy in information synthesis.

Core Features & Use Cases

Iterative Research Loop: Plans, searches, extracts, synthesizes, and stops research based on predefined criteria.
Cited Reports: Produces reports with inline citations, formatted to specific categories, and includes research statistics.
Use Case: For a user seeking a detailed report on a complex topic, this Skill can perform extensive research and compile a well-documented report.

Quick Start

Run the deep-research skill for a comprehensive analysis on "the impact of climate change on global economies".

Frequently Asked Questions about deep-research

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

FAQPage Schema

How do I automate multi-source research and generate a cited report?▼

Automate multi-source research by using an iterative loop that plans, searches, extracts, and synthesizes web data into a cited report. This process leverages LLM planning and web extraction to compile information with inline citations.

What is the best way to synthesize information from multiple web sources into one document?▼

The best way to synthesize information from multiple web sources is using an automated research loop. It gathers data via web search and extraction, then applies custom synthesis logic to compile findings into a single, formatted document with research statistics.

Does automated report generation work with web_search and web_extract for broad topics?▼

Yes, automated report generation works with web_search and web_extract dependencies to handle broad topics. The LLM plans the research steps, delegates data gathering to these tools, and synthesizes the extracted content into a comprehensive report.

How does the research loop decide when to stop gathering information?▼

The research loop decides when to stop gathering information based on predefined criteria evaluated during the iterative planning phase. Once the LLM determines that sufficient data is collected, it halts web searches and begins the final synthesis.

Can I get inline citations and research statistics in an automated synthesis report?▼

Yes, you can get inline citations and research statistics in an automated synthesis report. The output is specifically formatted to include citations directly within the text and provides statistics detailing the research process.

What are the limitations of using LLM planning for deep research on complex topics?▼

A limitation of using LLM planning for deep research is the dependency on external web search and extraction tools. The quality of the final cited report is constrained by the accuracy of extracted web data and the predefined stopping criteria of the iterative loop.