deep-research

Produce a source-backed knowledge map from root problem to architecture.

2|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/Tomlord1122/tomtom-skill --skill deep-research-tomlord1122
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Tomlord1122/tomtom-skill/tree/main/skills/deep-research
Command: npx skills add https://github.com/Tomlord1122/tomtom-skill --skill deep-research-tomlord1122

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep research sessions require constructing comprehensive, grounded knowledge maps starting from first principles. This skill provides a structured method to identify root problems, map the landscape of approaches, and produce a navigable, source-backed understanding that supports independent judgment.

Core Features & Use Cases

  • Root-cause framing: identify the fundamental problem and the constraints that shape solutions.
  • Landscape mapping: chart historical approaches, trade-offs, and evolution from manual processes to current practices.
  • Architecture deep-dive: articulate core abstractions, data flows, and end-to-end operation with boundary conditions.
  • Source-backed outputs: compile primary sources and a bibliography for verification.
  • Use case example: a researcher builds a knowledge map of a technical domain to inform decision-making and strategy.

Quick Start

Ask the AI to generate a first-principles knowledge map for a chosen topic, detailing the root problem, landscape, architecture, and forward-looking frontiers.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I build a first-principles knowledge map for a technical domain?

A first-principles knowledge map structures a technical topic from root problem to architecture by charting landscape evolution and articulating core abstractions. It requires citing 3-5 primary sources with inline citations to separate evidence from inference.

What is the best way to map a technical landscape from manual processes to current practices?

The best way to map a technical landscape is to chart historical approaches and trade-offs from manual processes to current practices. This structured method identifies fundamental constraints and maps end-to-end architecture with traceable primary sources.

How do I articulate core abstractions and data flows for system architecture?

To articulate core abstractions and data flows, map end-to-end operations and boundary conditions within the architecture. This structured deep-dive approach connects fundamental root problems to system-level data flows using traceable primary sources.

Can I use systematic reasoning to separate evidence from inference in deep research?

Yes, systematic reasoning separates evidence from inference by requiring 3-5 cited primary sources and a bibliography. This structured method ensures your deep-dive knowledge map supports independent judgment through traceable, source-backed landscape mapping and architecture analysis.

When do I need primary sources and a bibliography for root-cause analysis?

You need primary sources and a bibliography for root-cause analysis when building architectural understanding of technical topics. Compiling 3-5 primary sources with inline citations ensures rigorous landscape evolution tracking and verifiable, source-backed outputs.

Does first-principles research work for mapping forward-looking frontiers and boundary conditions?

First-principles research works for mapping forward-looking frontiers by articulating end-to-end architecture and boundary conditions. It systematically connects fundamental root constraints to future frontiers, delivering a layered output with a verifiable bibliography.