deep-research

Orchestrate multi-phase research pipelines and generate citation-backed reports.

32|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/t0dorakis/murmur --skill deep-research-t0dorakis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/t0dorakis/murmur/tree/main/.agents/skills/deep-research
Command: npx skills add https://github.com/t0dorakis/murmur --skill deep-research-t0dorakis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and templates (resource) components.

What problem does it solve?

This Skill automates the process of conducting in-depth, multi-source research, overcoming the limitations of basic web searches and providing verified, citation-backed reports.

Core Features & Use Cases

  • Comprehensive Analysis: Conducts deep dives into complex topics, comparisons, and trend analyses.
  • Verified Claims: Ensures all factual statements are backed by multiple sources and cross-referenced.
  • Source Credibility Scoring: Evaluates the trustworthiness of each source used.
  • Automated Reporting: Generates detailed reports in Markdown, HTML, and PDF formats.
  • Use Case: Use this Skill when you need a thorough understanding of a market, technology, or scientific field, complete with actionable insights and verifiable evidence, far exceeding what basic AI research tools can provide.

Quick Start

Use deep research to analyze the current state of AI agent frameworks in 2025.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I conduct deep research with automated source verification and synthesis?

Deep research with automated source verification is orchestrated through a multi-phase pipeline that collects data, performs rigorous triangulation across multiple sources, and generates comprehensive citation-backed reports to eliminate unverified claims.

Can I generate citation-backed research reports in multiple formats like Markdown and PDF?

Yes, citation-backed research reports can be automatically generated in Markdown, HTML, and PDF formats after the data collection and synthesis pipeline completes its multi-phase analysis.

What is the best way to overcome information overload when analyzing complex topics?

Overcoming information overload when analyzing complex topics is best handled by synthesizing data from multiple sources, scoring source credibility, and performing automated validation to ensure all factual statements are cross-referenced.

Does this research pipeline support different depth modes for quick analysis versus deep dives?

Yes, the research pipeline supports multiple depth modes including quick, standard, deep, and ultradeep, allowing you to scale the data collection and synthesis process based on the complexity of the analysis required.

How does source credibility scoring work during data collection?

Source credibility scoring evaluates the trustworthiness of each data source during the collection phase, ensuring that the final synthesized report relies on verified and cross-referenced factual statements rather than unverified claims.

When should I not use an enterprise-grade deep research pipeline for market or technology analysis?

You should not use an enterprise-grade deep research pipeline when a basic web search suffices, as this multi-phase triangulation and automated validation process is designed for complex topics requiring verifiable evidence and comprehensive analysis.