research-from-prd

Name: research-from-prd
Availability: InStock
Author: josemerca

Automate user research design and execution with a 6-block JTBD process.

25|5|Updated May 1, 2026

Search Tags:#user research #jobs-to-be-done #Mom Test #JTBD analysis #Field Study

Ready to run

npx skills add https://github.com/josemerca/mercadona-user-story-toolkit --skill research-from-prd

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-from-prd
Source: https://github.com/josemerca/mercadona-user-story-toolkit/tree/main/skills/research-from-prd
Command: npx skills add https://github.com/josemerca/mercadona-user-story-toolkit --skill research-from-prd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scikit-learn, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of designing and executing structured user research, providing a 6-block process that leverages Jobs-to-be-Done (JTBD) analysis and combines Mom Test and Field Study techniques to ensure a rigorous discovery process leading to actionable insights.

Core Features & Use Cases

6-Block Discovery Process: Facilitates a comprehensive approach to user research, including Preparation, Purpose, Plan, Criterions, Analysis, and Next Steps.
JTBD Analysis: Utilizes a Jobs-to-be-Done (JTBD) lens to deeply understand user motivations and behaviors.
Mom Test and Field Study: Combines quantitative and qualitative research methods to gather robust insights.
Use Case: Ideal for product managers, researchers, and designers seeking to uncover user needs and inform product development.

Quick Start

Execute the 'research-from-prd' skill and input your PRD to begin the structured research process.

Frequently Asked Questions about research-from-prd

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

FAQPage Schema

How do I structure user research using Jobs-to-be-Done analysis?▼

Jobs-to-be-Done analysis structures user research by framing user motivations and behaviors through a 6-block process: Preparation, Purpose, Plan, Criterions, Analysis, and Next Steps. This ensures a rigorous discovery process that combines qualitative and quantitative data for actionable product insights.

What is the Mom Test technique and when do I need it for product discovery?▼

The Mom Test is a user research technique focused on asking questions that gather unbiased facts about user behaviors rather than opinions. You need it during product discovery to validate user needs rigorously, preventing false positives when combined with Field Study methods and JTBD analysis.

How do I conduct a Field Study combined with JTBD analysis for UX research?▼

Conduct a Field Study combined with JTBD analysis by executing a structured 6-block discovery process that integrates quantitative observation with qualitative user motivation analysis. This approach leverages Python scripts to automate data synthesis, ensuring robust customer insights for product development.

Do I need Python and pandas to automate user research and JTBD synthesis?▼

Yes, you need Python along with pandas, numpy, and scikit-learn to automate user research and JTBD synthesis. These dependencies enable the script execution required for analyzing and synthesizing the qualitative and quantitative data gathered during the 6-block discovery process.

What's the best way to uncover user needs from a PRD for product development?▼

The best way to uncover user needs from a PRD is to input the document into an automated structured research process that applies a JTBD lens. This 6-block method integrates Mom Test and Field Study techniques to transform product requirements into actionable user insights.

Can I use this 6-block discovery process for both qualitative and quantitative data analysis?▼

Yes, you can use the 6-block discovery process for both qualitative and quantitative data analysis. It combines Mom Test techniques for qualitative insights with Field Study methods for quantitative data, utilizing Python scripts to synthesize comprehensive user research results.