research

Analyze topics by defining questions, separating facts from interpretations, and reporting uncertainty.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/nowonbun/nowonbun-harness --skill research-nowonbun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/nowonbun/nowonbun-harness/tree/main/codex-skills/action-management_research
Command: npx skills add https://github.com/nowonbun/nowonbun-harness --skill research-nowonbun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Engineers who perform topic analysis need a disciplined approach to define questions, separate facts from interpretations, compare diverse viewpoints, and clearly express uncertainty to support better decision-making.

Core Features & Use Cases

  • Question design enforcement: Define scope, time range, and reliability requirements before analysis.
  • Evidence separation discipline: Separate facts, interpretations, hypotheses, and predictions with explicit confidence levels.
  • Viewpoint comparison: Present multiple perspectives with explicit premises and limits.
  • Uncertainty reporting: Quantify and communicate uncertainty to stakeholders for informed decisions.

Quick Start

Define the research question, set scope and trust level, then structure the analysis to separate facts, interpretations, and hypotheses.

Frequently Asked Questions about research

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

FAQPage Schema
How do I separate facts from interpretations when analyzing a research topic?

To separate facts from interpretations during topic analysis, define your research question scope first, then categorize evidence into facts, interpretations, hypotheses, and predictions with explicit confidence levels. This structured research approach ensures stakeholders understand the reliability of each data point before making decisions.

What is the best way to compare multiple viewpoints in a structured analysis?

Comparing viewpoints in structured analysis requires presenting multiple perspectives with explicit premises and clearly defined limits. By defining the research question scope and trust levels upfront, you can systematically evaluate conflicting interpretations across domains like history, geopolitics, economics, and technology while maintaining analytical rigor.

How do I quantify and report uncertainty to support decision-making?

Quantifying uncertainty for decision-support involves assigning explicit confidence levels to each piece of evidence, separating verified facts from hypotheses, and clearly communicating these confidence metrics to stakeholders. This uncertainty reporting discipline ensures informed decisions by making the limits of evidence transparent across research domains.

Can I use structured reasoning to analyze topics across different domains like history and technology?

Structured reasoning applies to topic analysis across domains such as history, geopolitics, economics, and technology. The approach enforces question design, evidence separation, viewpoint comparison, and uncertainty reporting, making it effective for any research task requiring decision-support where structured analysis and clear reporting are needed.

What should I define before starting a topic analysis to ensure reliable results?

Before starting topic analysis, you must define the research question scope, time range, and reliability requirements. This question design enforcement step establishes trust levels and analytical boundaries upfront, ensuring the subsequent separation of facts, interpretations, and hypotheses remains disciplined and aligned with stakeholder decision-support needs.

Why does my research analysis mix facts with interpretations and confuse stakeholders?

Research analysis confuses stakeholders when facts and interpretations are not explicitly separated with confidence levels. Applying evidence separation discipline categorizes findings into distinct tiers of facts, interpretations, hypotheses, and predictions, ensuring uncertainty is clearly reported and stakeholders can make informed decisions based on verified reliability.