Skip to main content
skill CX Codex

user-persona-creation — Claude Code skill: what it does & install

Builds realistic user personas from qualitative research and interview notes. Useful for guiding product design and feature prioritization.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add aj-geddes/useful-ai-prompts --skill user-persona-creation -a claude-code
Open on GitHub

What user-persona-creation does

This skill turns user research into actionable profiles for engineering and product teams. It outlines specific questionnaire modules covering demographics, goals, pain points, and current user behaviors. Detailed reference files live in the references/ directory, including research-data-collection.md, persona-template.md, multiple-personas.md, and using-personas.md.

The workflow expects empirical input. Its starter interview guide targets a sample size of 12 respondents and emphasizes capturing verbatim quotes. Without raw research data, the resulting personas will only reflect team guesses.

Guidance in the repository limits teams to 2–3 primary personas and explicitly warns against building more than 4, keeping feature decisions focused on core target segments.

What it helps with

  • structure discovery interview questions covering demographics, goals, and frustrations
  • convert qualitative research notes into 2–3 primary user personas
  • align roadmap priorities with documented user pain points
  • extract direct user quotes for journey mapping

Example prompts for the agent

  • Create an interview guide for 12 target users following the user-persona-creation structure.
  • Synthesize interview notes in research.txt into 2 primary personas using persona-template.md.
  • Map pain points from our user personas to this quarter's feature roadmap.

How to install user-persona-creation

1Skills CLI (Vercel)

npx skills add aj-geddes/useful-ai-prompts --skill user-persona-creation -a claude-code

2Manually: put the files in place

~/.claude/skills/user-persona-creation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/user-persona-creation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about user-persona-creation

How to install user-persona-creation in Claude Code?

Run npx skills add aj-geddes/useful-ai-prompts --skill user-persona-creation -a claude-code. The file will be placed at ~/.claude/skills/user-persona-creation/SKILL.md.

How many personas should be created?

The author recommends 2–3 primary personas and advises against defining more than 4 primary profiles.

What reference guides are included?

The references/ directory includes guides for data collection, a persona template, handling multiple personas, and applying them across decisions.

Source text

SKILL.md · MIT
---
name: user-persona-creation
description: >
  Create detailed user personas based on research and data. Develop realistic
  representations of target users to guide product decisions and ensure
  user-centered design.
---

# User Persona Creation

## Table of Contents

- [Overview](#overview)
- [When to Use](#when-to-use)
- [Quick Start](#quick-start)
- [Reference Guides](#reference-guides)
- [Best Practices](#best-practices)

## Overview

User personas synthesize research into realistic user profiles that guide design, development, and marketing decisions.

## When to Use

- Starting product design
- Feature prioritization
- Marketing messaging
- User research synthesis
- Team alignment on users
- Journey mapping
- Success metrics definition

## Quick Start

Minimal working example:

```python
# Gather data for persona development

class PersonaResearch:
    def conduct_interviews(self, target_sample_size=12):
        """Interview target users"""
        interview_guide = {
            'demographics': [
                'Age, gender, location',
                'Job title, industry, company size',
                'Experience level, education',
                'Salary range, purchasing power'
            ],
            'goals': [
                'What are you trying to achieve?',
                'What's most important to you?',
                'What does success look like?'
            ],
            'pain_points': [
                'What frustrates you about current solutions?',
                'What takes too long or is complicated?',
                'What prevents you from achieving goals?'
            ],
            'behaviors': [
                'How do you currently solve this problem?',
                'What tools do you use?',
// ... (see reference guides for full implementation)
```

## Reference Guides

Detailed implementations in the `references/` directory:

| Guide | Contents |
|---|---|
| [Research & Data Collection](references/research-data-collection.md) | Research & Data Collection |
| [Persona Template](references/persona-template.md) | Persona Template |
| [Multiple Personas](references/multiple-personas.md) | Multiple Personas |
| [Using Personas](references/using-personas.md) | Using Personas |

## Best Practices

### ✅ DO

- Base personas on real research, not assumptions
- Include 2-3 primary personas
- Make personas specific and detailed
- Include direct user quotes
- Update personas based on new data
- Share personas across organization
- Use personas for all product decisions
- Include both goals and pain points
- Create personas for different user types
- Document research sources

### ❌ DON'T

- Create personas without research
- Create too many personas (>4 primary)
- Make personas too generic
- Ignore data in favor of assumptions
- Create personas, then forget them
- Use personas only for design
- Make personas unrealistically perfect
- Ignore secondary users
- Keep personas locked away
- Never update personas

© aj-geddes · MIT · aj-geddes/useful-ai-prompts

Similar skills

Everything for Design →

From the same set143

database-performance-debugging A skill that walks your agent through finding slow SQL queries and reading their execution plans. Useful when the app drags or the database burns CPU. CX Codex +1 493installs code-documentation A skill that makes the agent write documentation inside your code: JSDoc, Python docstrings, JavaDoc, inline comments and API notes. Useful when functions and classes need describing, not rewriting. CX Codex +1 492installs reactive-programming A skill for reactive streams in RxJS: observables, operators, backpressure. Useful when a project leans on async data and events. CX Codex +1 491installs api-pagination A skill that tells the agent how to page through big collections: offset/limit, cursors, keyset. Useful when a user list or search result set outgrows one response. CX Codex +1 489installs nosql-database-design Guides the agent through NoSQL schema work: MongoDB collections, DynamoDB tables, embedding vs referencing, indexes. Useful before the schema hardens in code. CX Codex +1 486installs database-indexing-strategy A skill for planning indexes: picks the type, builds composite and partial ones, covers maintenance. Useful when queries slow down. CX Codex +1 486installs uptime-monitoring A skill that walks your coding agent through uptime checks, a public status page and incident tracking. Useful when you need to know which dependency actually broke. CX Codex +1 484installs api-response-optimization A coding-agent skill that trims payloads, adds caching and compression, and gives you a checklist for slow API endpoints. CX Codex +1 484installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor