# Turn UX Research into Actionable Personas

Research data can be difficult to synthesize into clear design direction. This skill generates structured personas, scenarios, confidence labels, and design implications from user records.

## Install

```bash
npx skillstore add davila7/ux-researcher-designer
```

## Metadata

- Status: approved
- Slug: davila7-ux-researcher-designer
- Skillstore revision: r2
- Version status: missing
- Tree hash: 917d1b909d1d2e097666a32b4c6c7d821daa60b31be9c3d2203c77a2adf0da69
- Author: davila7
- GitHub username: davila7
- License: MIT
- Repository: https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/creative-design/ux-researcher-designer
- Ref: c43861a65bb95efcae259cd161c9d6f4dc7eec6f
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 76
- Public page: https://skillstore.pages.dev/skills/davila7-ux-researcher-designer
- Manifest: https://skillstore.pages.dev/api/skills/davila7-ux-researcher-designer/manifest

## Capabilities

- Analyzes usage frequency, feature adoption, devices, contexts, and pain points from prepared user records.
- Classifies a dataset as power user, casual user, business user, or mobile-first using fixed heuristics.
- Aggregates age range, location type, and technology proficiency into a persona demographic profile.
- Combines optional interview goals, needs, motivations, values, and quotes with behavioral patterns.
- Produces persona scenarios, design implications, sample-size confidence labels, and formatted text or JSON output.

## Use Cases

- Synthesize Discovery Research: Synthesize prepared behavioral records and interview notes into an evidence-linked draft persona for a discovery study.
- Guide Interface Concepts: Translate a defined user segment into needs, frustrations, scenarios, and interface implications before concept design.
- Compare Product Segments: Create comparable persona drafts for separately prepared segments when planning priorities with a cross-functional team.

## Prompt Templates

### Create a Basic Persona

```
Use the persona generator with these prepared user records. Return the archetype, demographics, goals, frustrations, scenario, and confidence label: [records]
```

### Add Interview Evidence

```
Generate a persona from these user records and interview insights. Separate observed inputs, heuristic conclusions, default content, and design implications: [data]
```

### Compare Prepared Segments

```
Generate one persona for each prepared segment. Compare archetypes, behaviors, needs, frustrations, confidence labels, and design implications without merging records: [segments]
```

### Review Segment Sensitivity

```
Run a sensitivity review across alternative segment definitions. Identify changed classifications, stable findings, default assumptions, evidence gaps, and recommended validation work: [dataset]
```

## Limitations

- The included command uses built-in sample data and does not load supplied research datasets.
- Each call creates one aggregate persona and does not discover multiple clusters within a dataset.
- Archetypes, scenarios, and several frustrations come from fixed heuristics and templates.
- Confidence labels use sample size only and do not represent statistical confidence or research validity.

## Best Practices

- Normalize fields and remove direct identifiers before providing research records.
- Prepare meaningful segments separately because each generator call produces one aggregate persona.
- Label defaults and heuristic conclusions, then validate them with participants and additional evidence.

## Anti Patterns

- Do not present generated names, default quotes, or template scenarios as direct research evidence.
- Do not treat one aggregate persona as proof of distinct market segments.
- Do not describe the sample-size label as statistical confidence or validated research quality.

## Security Audit

- Audited at: 2026-07-23T15:59:49.528\+00:00
- Summary: The only static finding is a false positive because Markdown backticks format a documented Python command and do not invoke Ruby or a shell. The local script has no subprocess, network, credential, or filesystem behavior, and no semantic threats or prompt injection were found.

## Stats

- Views: 211
- Downloads: 9
- Favorites: 0
- Popularity score: 0