deep-research

Decompose questions into sub-questions and synthesize cited reports from multi-source research.

582|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/shobcoder/shob --skill deep-research-shobcoder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/shobcoder/shob/tree/main/skills/research-knowledge
Command: npx skills add https://github.com/shobcoder/shob --skill deep-research-shobcoder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Complex questions often require deep, verifiable research. This skill orchestrates a multi-phase workflow to produce a structured, source-backed synthesis rather than noisy results.

Core Features & Use Cases

  • Multi-phase research loop: query decomposition, multi-source crawling, claim extraction, cross-referencing, conflict resolution, and synthesized reporting.
  • Inline citations: every claim is traceable to its source.
  • Use Case: when you need in-depth, defensible answers for research, policy, or technical evaluation.

Quick Start

Provide a complex question to initiate a multi-phase deep research run.

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 with verifiable citations?

To automate multi-source research with verifiable citations, you provide a complex question. The system decomposes it into sub-questions, crawls multiple sources, cross-references claims, and delivers a synthesized report with inline source citations.

What is the best way to resolve conflicting information from multiple research sources?

The best way to resolve conflicting information from multiple research sources is using a conflict resolution mechanism. This system cross-references extracted claims during multi-source crawling to ensure a verifiable synthesis.

How does query decomposition improve deep research results?

Query decomposition improves deep research results by breaking complex user questions into atomic sub-questions. This targets multi-source crawling and claim extraction, ensuring structured, source-backed synthesis rather than noisy results.

Can I get inline citations for high-stakes decision making research?

Yes, you can get inline citations for high-stakes decision making research. The system delivers a structured report where every claim is traceable to its source, ensuring defensible answers for policy or technical evaluation.

When do I need automated cross-referencing for source synthesis?

You need automated cross-referencing for source synthesis when complex questions require deep, verifiable research. It orchestrates multi-source crawling and conflict resolution to produce structured, source-backed answers instead of noisy results.