deep-research

Decompose complex topics into subtopics for parallel agent research and synthesize findings into a unified report with ACM citations.

8|Updated Nov 29, 2025
One-click install
npx skills add https://github.com/Pyroxin/opinionated-claude-skills --skill deep-research-pyroxin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Pyroxin/opinionated-claude-skills/tree/main/opinionated-research/skills/deep-research
Command: npx skills add https://github.com/Pyroxin/opinionated-claude-skills --skill deep-research-pyroxin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill tackles complex research topics by breaking them down, delegating to specialized agents, and synthesizing findings into a comprehensive report, ensuring diverse perspectives and cross-referenced insights.

Core Features & Use Cases

  • Topic Decomposition: Breaks down complex subjects into manageable subtopics.
  • Parallel Agent Delegation: Assigns subtopics to specialized research agents for efficient, concurrent investigation.
  • Cross-Referencing & Synthesis: Weaves together findings from multiple agents to reveal overarching themes and connections.
  • Use Case: Researching the "impact of quantum computing on cybersecurity" by delegating subtopics like "quantum algorithms for code-breaking," "post-quantum cryptography standards," and "current cybersecurity vulnerabilities" to different agents, then synthesizing their reports into a unified analysis.

Quick Start

Use the deep-research skill to investigate the topic of "sustainable urban planning models".

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I research complex topics requiring diverse sources and cross-referencing?

Researching complex topics is handled by decomposing the subject into subtopics, delegating them to specialized agents for concurrent investigation, and synthesizing the findings into a unified report with cross-referenced insights.

What is multi-agent topic decomposition for information retrieval?

Topic decomposition is the process of breaking down a complex subject into manageable subtopics, assigning each to a specialized research agent for parallel information retrieval, and then weaving together their findings to reveal overarching themes.

How do I synthesize findings from parallel research agents into a unified report?

Synthesizing findings from parallel agents involves cross-referencing the diverse perspectives gathered during concurrent investigation and weaving them together into a comprehensive unified report with ACM citations.

Can I use parallel agent delegation for investigating broad subjects like sustainable urban planning?

Parallel agent delegation supports investigating broad subjects by assigning specialized subtopics to different agents concurrently, ensuring diverse perspectives and cross-referenced insights for thorough complex topic analysis.

What is the best way to cross-reference multiple information sources for a research synthesis?

The best way to cross-reference multiple sources is using an orchestrated multi-agent approach that delegates subtopics to specialized agents, ensuring cross-referenced insights are synthesized into a unified report with ACM citations.

When should I not use a multi-agent decomposition approach for research?

Multi-agent decomposition is not suited for simple, single-source lookups, as the overhead of orchestrating parallel agents and synthesizing cross-referenced findings is designed specifically for complex topics requiring diverse sources.