deep-research

Dispatch a subagent to research topics and synthesize cited findings.

2|Updated Dec 20, 2020
One-click install
npx skills add https://github.com/buvis/home --skill deep-research-buvis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/buvis/home/tree/main/.claude/skills/research
Command: npx skills add https://github.com/buvis/home --skill deep-research-buvis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps researchers and teams obtain in-depth, multi-source research while keeping the main context clean and organized for actionable decisions.

Core Features & Use Cases

  • Dispatches a subagent to perform structured literature reviews, technology comparisons, and competitive analyses.
  • Synthesizes findings from multiple sources into a cohesive report with citations and date stamps.
  • Use Case: When you need a comprehensive answer that integrates sources from academic papers, official docs, and reputable blogs.

Quick Start

Provide a topic and sub-questions, and I will generate a structured, multi-source research report.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I conduct a multi-source literature review without losing track of citations?

You can conduct a multi-source literature review by dispatching a subagent to handle 3-5 focused sub-questions, querying WebSearch and WebFetch, and synthesizing cross-source findings into a cohesive report with rigorous source citations and date stamps for reproducibility.

What is multi-source synthesis for competitive analysis and how does it work?

Multi-source synthesis for competitive analysis works by dispatching a dedicated subagent that queries multiple web sources, integrates findings from official docs and reputable blogs, and outputs a structured report with traceable citations and date stamps.

How do I structure a prompt for comprehensive technology comparisons using web search?

To structure a prompt for technology comparisons, provide your topic and 3-5 focused sub-questions, enabling the subagent to leverage WebSearch and WebFetch tools and apply rigorous citation rules to generate a structured, multi-source research report.

Can I use this approach to research academic papers and official documentation together?

Yes, you can research academic papers and official documentation together by providing a topic and sub-questions, which triggers a subagent to fetch and synthesize findings from multiple source types into a cohesive, cited report.

What are the limitations of using a subagent for deep research and cross-source synthesis?

Limitations of subagent-based deep research include the requirement for a structured prompt template and the confinement of queries to 3-5 focused sub-questions, meaning overly broad topics may lack comprehensive coverage or require multiple sequential runs.