102.7K+Download
Skip to the usage guide
ux-researcher-designerby Alireza Rezvani

UX Researcher Designer Skill.

A Claude Code and Codex skill for UX research: data-driven personas, journey maps, usability testing frameworks, and research synthesis.

  • UX & Research
  • Research document
Download OpenDesignView usage guide
alirezarezvani/claude-skills · product-team/skills/ux-researcher-designer/SKILL.mdSKILL.md
--- name: ux-researcher-designer description: UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use when conducting user research, creating personas, mapping user journeys, planning usability tests, or validating designs. --- ## Trigger Terms ## Workflows ## Quick Reference Tables ## Knowledge Base ## Validation Checklist ## Related Skills
Front matter and section headings read from the upstream file on 2026-09-14 · 11,912 characters in full

01 What it does

What the ux-researcher-designer Skill Does in Claude Code and Codex

Summary, workflow and outputs, all read from the skill's SKILL.md.

From the SKILL.mdRead 2026-09-14 · not a recorded run

In the Skill's Own Terms

A UX research and design toolkit for a Senior UX Designer or Researcher. It runs four workflows: generate a data-driven persona, create a journey map, plan a usability test and synthesize research, with trigger terms that route each request to the right one.

The persona workflow prepares structured user records and uses a bundled persona_generator.py script for text or JSON output. The entry file shows output-format commands, not how a user-data file is loaded: inspect the bundled script before assuming an input flag. Reference tables cover methods, sample-size heuristics, issue severity and interview questions; they do not establish research validity on their own.

What it produces

  • A persona covering demographics, psychographics, behaviors, needs and goals, frustrations with evidence, scenarios, design implications and data points.
  • Either a human-readable persona block or JSON for integration, depending on the argument passed.
  • A journey map with actions, touchpoints, emotions, pain points and opportunities filled in for every stage.
  • Synthesized findings that state frequency as X out of Y participants alongside evidence, business impact and a recommendation.
  • A usability test plan with research questions, scenarios, success criteria and a method suited to the study.
See the example prompt ↗

How It Works

  1. 01
    Pick the Right Workflow

    The skill is split into four workflows: persona generation, journey mapping, usability test planning and research synthesis.

  2. 02
    Run the Persona Generator

    Persona generation is a script call. Run it with no argument for human-readable output, or pass json to get machine-readable output for integration.

  3. 03
    Review the Generated Components

    The workflow gives a review table so you check the archetype against data patterns, the goals for actionability, frustrations for frequency counts, and the design implications for whether designers can act on them.

  4. 04
    Validate the Persona

    A generated persona is not finished until you take it back to 3-5 real users and ask whether it sounds like them.

  5. 05
    Map the Journey

    Journey mapping uses typical B2B SaaS stages, then fills each stage with actions, touchpoints, emotions, pain points and opportunities.

  6. 06
    Code and Cluster the Research

    Raw data is tagged with GOAL, PAIN, BEHAVIOR, CONTEXT and QUOTE, then similar patterns are clustered into segments with sizes before findings are extracted.

02 Find your fit

When to Use the ux-researcher-designer Skill

Use the ux-researcher-designer skill in Claude Code or Codex when the job is UX research of this kind. Fit and limits below are taken from the skill's own file.

Good Fit

  • You have analytics, survey or interview data and need a research-backed persona rather than a guess.
  • You need to visualize the end-to-end experience for one specific user goal.
  • You have a design to validate with real users and need a test plan.
  • You are sitting on raw interviews, surveys or observations and need actionable insights out of them.

Know the Boundaries

  • Journey maps built on assumptions rather than real user data fail the quality checklist.
  • Usability tasks written as instructions instead of realistic scenarios do not pass.
  • Small or unrepresentative samples limit what a persona can support. The source’s sample-size bands are planning heuristics, not proof that a persona represents the wider audience.

What to Provide

  • User records as JSONWorkflow 1 expects a JSON array with one object per user carrying user_id, age, usage_frequency, features_used, primary_device, usage_context, tech_proficiency and pain_points.
  • Journey scopeDefine the persona, the goal, the start trigger, the end success criteria and the timeframe before mapping.
  • Journey data sourcesJourney stages are populated from interviews, session recordings, analytics such as funnels and drop-offs, and support tickets.
  • The design and your research goalsThe usability workflow starts from the design you want to validate plus your vague goals, which you then transform into testable questions.

03 Inside the skill

Rules the ux-researcher-designer Skill Gives Claude Code and Codex

8 concrete instructions, defaults and limits the SKILL.md sets for the agent — the part of the file that changes the result.

  1. Turn Vague Goals into Testable Questions

    Before testing, rewrite vague aims into measurable ones, for example "Is it easy to use?" becomes "Can users complete checkout in <3 min?".

  2. Match the Method to the Depth You Need

    Moderated remote sessions default to 5-8 participants over 45-60 minutes, unmoderated remote to 10-20 participants over 15-20 minutes, and guerrilla testing to 3-5 participants over 5-10 minutes.

  3. Set Metrics for the Actual Study

    The source gives example targets such as completion above 80% and satisfaction above 4/5. Choose and document thresholds appropriate to the task and study before evaluating results; these are not universal pass criteria.

  4. Write Tasks as Scenarios, Not Instructions

    Each task gets a SCENARIO, a GOAL and a SUCCESS line, and tasks progress warm-up, core, secondary, edge case, free exploration.

  5. Treat Sample-Size Bands as Heuristics

    The source labels 5–10 users exploratory, 11–30 directional and 31+ high confidence. Sample size alone does not establish confidence or production readiness: recruitment, data quality and coverage still matter.

  6. Meet the Persona Quality Bar

    Its persona checklist asks for at least 20 users and two qualitative/quantitative sources, while its table also describes smaller exploratory samples. State which level the available evidence supports and leave unmet checks explicit.

  7. Prioritize with the Priority Score

    Opportunities are ranked by multiplying frequency, severity and solvability rather than by gut feel.

  8. Do Not Build Themes on Thin Data

    Synthesis patterns must rest on three or more data points before they become a finding.

04 Put it to work

Install ux-researcher-designer in Claude Code or Codex

One npx skills add command, then a first task in your agent and a checklist for the result.

Add ux-researcher-designer to Claude Code, Codex or Your Agent

Run in your project; the installer asks which agent to add it to.

Terminal
npx skills add https://github.com/alirezarezvani/claude-skills --skill ux-researcher-designer

Generic skills CLI form for product-team/skills/ux-researcher-designer/SKILL.md; the repository may document its own path.

Give the Skill a First UX Research Task

Written in the skill's own terms; replace the bracketed parts with your material.

Starter prompt
Here is our recent research on [product area]: [paste the JSON user data with usage_frequency, features_used and pain_points per user]. Generate a data-driven persona from it and tell me the archetype, the design implications and the evidence limits, recruitment coverage and remaining uncertainty. Then map the journey for that persona from [trigger event] to [success criteria] and rank the opportunities so I know what to fix first.

Editorial example based on the reviewed source; not an executed task or an upstream quotation.

Check the First Result

What the SKILL.md itself says a correct result looks like:

  • State the actual participant count, recruitment limits, sources and uncertainty. Do not convert a sample-size band into a guarantee of confidence.
  • Confirm the journey map has every layer filled, including actions, touchpoints and emotions, plus pain points per stage and prioritized opportunities.
  • Confirm the usability test has testable research questions, realistic task scenarios, 5+ participants per design, defined success metrics and severity ratings in the findings.
  • Confirm the synthesis has consistently coded data, patterns on 3+ data points, evidence behind findings, actionable recommendations and justified priorities.
  • Validate the persona outside the research itself by cross-checking it against support tickets and your analytics.

OpenDesign provides a local workspace for coding agents. Check the installed version for skill availability and setup; this source review does not verify bundled skills or include external tools and services.

Download OpenDesignRead the quickstart

05 Open source, traceable

Source, License and Verification

Where this page's facts come from, and when they were last checked.

Author
Alireza Rezvani
Repository
github.com/alirezarezvani/claude-skills Branch main
Skill file
product-team/skills/ux-researcher-designer/SKILL.md Content checksum recorded at verification; commit 19392f7
License
MIT From LICENSE.
Repository stars
25,934 GitHub snapshot taken 2026-09-14 for the whole alirezarezvani/claude-skills repository, which contains 5 skills in this catalog. Not a rating or usage count for ux-researcher-designer.
Verified by OpenDesign
2026-09-14 Source file, path, license text and star count were checked. Not bundled in OpenDesign main (checked 2026-08-28); a live run has not been recorded on this page.

Inside the SKILL.md

  1. Trigger TermsTwelve phrases that route a request here, such as generate persona from data or map user journey.
  2. WorkflowsFour workflows, each with a situation, numbered steps, decision tables and a reference pointer.
  3. Tool ReferenceDocuments persona_generator.py, its arguments, sample output, four archetypes and output components.
  4. Quick Reference TablesMethod selection, persona confidence by sample, usability issue severity and interview question types.
  5. Knowledge BaseLists the four guides in references/ and what each one contains.
  6. Validation ChecklistPer-artifact checklists for persona, journey map, usability test and synthesis quality.
  7. Related SkillsPoints to the UI design system and product manager toolkit skills.
The Skill's Own Description
“UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use when conducting user research, creating personas, mapping user journeys, planning usability tests, or validating designs.”

Front-matter description from SKILL.md. The full file is about 11,912 characters. Read the full file on GitHub.

06 Before you install

Questions About the ux-researcher-designer Skill

Answers come from the SKILL.md as read on 2026-09-14, not from a recorded run.

How many people do I need for each kind of research question?

The source suggests 8–15 participants for interviews and 5–8 for usability tests as planning examples. Choose the study size for the audience, method and question; those ranges are not a universal minimum or a statistical guarantee.

Does it help me write interview questions?

Yes, the quick reference gives five question types with sample wording: context, behavior, goals, pain and reflection. Each one is tied to what it is useful for, for example reflection questions like "What would you change?" generate ideas.

How do I decide which usability issues to fix first?

The severity table ranks issues 4 down to 1. Critical prevents task completion and must be fixed immediately, Major causes significant difficulty and is fixed before release, Minor causes hesitation, Cosmetic is low priority.

Does it ship reference documentation?

Yes, four guides sit in references/: persona-methodology.md, journey-mapping-guide.md, example-personas.md and usability-testing-frameworks.md. The example file contains 3 complete personas with data, and the usability guide covers test planning, task design and analysis.

UX Researcher Designer

Run ux-researcher-designer on a Real UX Research Task.

Download OpenDesign, import ux-researcher-designer from its SKILL.md link, paste the prompt above, and read the plan before the result.

Download OpenDesignBrowse all skills
Terminal
npx skills add https://github.com/alirezarezvani/claude-skills --skill ux-researcher-designer