deep-research

Execute an 8-phase research pipeline with source retrieval and report generation.

1|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/mrsono0/lecture_factory --skill deep-research-mrsono0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/mrsono0/lecture_factory/tree/main/.claude/skills/deep-research
Command: npx skills add https://github.com/mrsono0/lecture_factory --skill deep-research-mrsono0

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of conducting in-depth, multi-source research, providing verified, citation-backed reports that rival and exceed the capabilities of commercial AI research tools. It eliminates the need for manual literature review, source verification, and report compilation.

Core Features & Use Cases

  • Comprehensive Research: Conducts deep analysis using an 8-phase pipeline (Scope, Plan, Retrieve, Triangulate, Synthesize, Critique, Refine, Package).
  • Verified Claims: Ensures all major claims are backed by at least 3 independent sources and flags contradictions.
  • Source Credibility Scoring: Evaluates each source on a 0-100 scale for authority, recency, expertise, and bias.
  • Automated Reporting: Generates professional Markdown, HTML (McKinsey-style), and PDF reports with full bibliographies and methodology appendices.
  • Use Case: Use this Skill to research complex topics like "the state of quantum computing in 2025" or to compare competing technologies like "PostgreSQL vs. Supabase" for critical decision-making.

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 automate deep research and generate citation-backed reports?

Automate deep research by executing an 8-phase pipeline that handles source retrieval, triangulation, and synthesis to generate citation-backed reports. It evaluates source credibility and outputs professional Markdown, HTML, and PDF files with full bibliographies.

How does source verification work during multi-source research analysis?

Source verification works by triangulating major claims across at least 3 independent sources and flagging contradictions. Each source receives a 0-100 credibility score evaluating its authority, recency, expertise, and bias to ensure research reliability.

Can I use this to compare competing technologies for critical decision-making?

Yes, you can compare competing technologies for critical decision-making by running a deep research analysis. The Skill synthesizes multiple verified sources into comprehensive reports, providing clear comparisons for complex topics like database architectures.

What is the best way to research complex topics quickly?

The best way to research complex topics quickly is using the quick research mode for rapid analysis. For more depth, standard, deep, and ultradeep modes apply Graph-of-Thoughts reasoning and parallel agent execution to accelerate comprehensive synthesis.

What are the limitations of automated report generation for enterprise research?

Automated report generation limitations include a strict dependency on the availability and quality of external sources for credibility scoring. While it automates synthesis and critique, the final packaged report requires human review to contextualize highly nuanced or contradictory domain findings.