$npx -y skills add cuellarfr/design-skills --skill ux-researchPlan, conduct, and analyze UX research using proven methodologies. Use when planning user research, writing interview scripts, creating test plans, recruiting participants, analyzing qualitative data, or synthesizing findings into actionable insights. Covers generative, evaluativ
| 1 | # UX Research |
| 2 | |
| 3 | Plan, conduct, and analyze user research that produces actionable insights for product design. This skill provides frameworks, methods, and practical guidance for every stage of the research process — from defining the right question to presenting findings that drive decisions. |
| 4 | |
| 5 | ## When to Use This Skill |
| 6 | |
| 7 | Use this skill when: |
| 8 | - Planning a research study (choosing methods, defining scope, writing a plan) |
| 9 | - Writing interview scripts or discussion guides |
| 10 | - Creating usability test plans with tasks and success metrics |
| 11 | - Recruiting participants and writing screener surveys |
| 12 | - Analyzing qualitative data (affinity diagrams, thematic analysis) |
| 13 | - Synthesizing research into personas, journey maps, or opportunity maps |
| 14 | - Setting up continuous discovery practices (weekly interviews, OSTs) |
| 15 | - Presenting findings and recommendations to stakeholders |
| 16 | |
| 17 | ## Core Principle |
| 18 | |
| 19 | Research is a tool for reducing risk, not a deliverable. The goal is always to inform decisions — not to produce documents. Research is not asking people what they like, not a political tool, and not science. It's applied inquiry that helps you solve the right problem. |
| 20 | |
| 21 | ## Research Types |
| 22 | |
| 23 | Choose your research type based on what decisions are in play: |
| 24 | |
| 25 | ### Generative / Exploratory |
| 26 | **When:** Before you know what you're building. You need to define the problem. |
| 27 | **Methods:** Interviews, field observation, contextual inquiry, diary studies, literature review |
| 28 | **Output:** Problem definition, opportunity areas, personas, mental models |
| 29 | |
| 30 | ### Descriptive |
| 31 | **When:** You have a design problem and need to fully understand the context. |
| 32 | **Methods:** Contextual inquiry, fly-on-the-wall observation, journey mapping, card sorting |
| 33 | **Output:** Current-state maps, workflow diagrams, mental models |
| 34 | |
| 35 | ### Evaluative |
| 36 | **When:** You have potential solutions and need to test them. |
| 37 | **Methods:** Usability testing, heuristic evaluation, A/B testing, click testing, tree testing |
| 38 | **Output:** Severity-ranked issues, task completion rates, recommendations |
| 39 | |
| 40 | ### Causal |
| 41 | **When:** A solution is live and you need to understand actual usage patterns. |
| 42 | **Methods:** Analytics review, A/B testing, funnel analysis, surveys |
| 43 | **Output:** Conversion data, behavioral patterns, quantitative validation |
| 44 | |
| 45 | ## The Research Process |
| 46 | |
| 47 | ### 1. Define the Problem |
| 48 | |
| 49 | Start with a clear problem statement. Base it on a verb that indicates outcome: |
| 50 | - **Good:** "Identify the barriers preventing users from completing onboarding" |
| 51 | - **Good:** "Evaluate whether the new checkout flow reduces abandonment" |
| 52 | - **Bad:** "Understand the user experience" (too vague) |
| 53 | - **Bad:** "Explore the problem space" (no measurable outcome) |
| 54 | |
| 55 | Write 3-5 research questions. More than 10 means your scope is too broad. |
| 56 | |
| 57 | ### 2. Select the Approach |
| 58 | |
| 59 | | You need to... | Use... | Time needed | |
| 60 | |---|---|---| |
| 61 | | Discover unmet needs | Generative interviews | 2-3 weeks | |
| 62 | | Understand context and workflows | Contextual inquiry | 1-2 weeks | |
| 63 | | Test a design concept | Usability testing | 3-5 days | |
| 64 | | Validate with numbers | Survey + analytics | 1-2 weeks | |
| 65 | | Quick expert review | Heuristic evaluation | 1-2 days | |
| 66 | | Prioritize features | Card sorting, buy-a-feature | 1 week | |
| 67 | | Understand navigation mental models | Tree testing, card sorting | 1 week | |
| 68 | | Track ongoing patterns | Continuous discovery (weekly) | Ongoing | |
| 69 | |
| 70 | See `references/research-methods-catalog.md` for detailed method descriptions. |
| 71 | |
| 72 | ### 3. Plan and Prepare |
| 73 | |
| 74 | Every study needs a written plan, even if it's brief. Use `templates/research-plan-template.md`. |
| 75 | |
| 76 | **Essential plan elements:** |
| 77 | - Problem statement and research questions |
| 78 | - Methodology and rationale |
| 79 | - Participant criteria and recruiting approach |
| 80 | - Number of participants (see benchmarks below) |
| 81 | - Timeline and logistics |
| 82 | - How data will be captured and stored |
| 83 | - Who will participate from the team |
| 84 | |
| 85 | **Participant benchmarks:** |
| 86 | - Usability testing: 3-5 per round (catch ~85% of issues with 5 users) |
| 87 | - Generative interviews: 5-8 per persona segment |
| 88 | - Card sorting: 15-20 for statistical patterns |
| 89 | - Surveys: 100+ for quantitative significance |
| 90 | - Continuous discovery: 1 per week minimum |
| 91 | |
| 92 | ### 4. Recruit Participants |
| 93 | |
| 94 | Recruiting is the hardest part. Embrace it — good recruiting puts the quality in your research. |
| 95 | |
| 96 | **A good participant:** |
| 97 | - Shares the goals and concerns of target users |
| 98 | - Embodies key characteristics (age, role, tech familiarity) |
| 99 | - Can articulate their thoughts clearly |
| 100 | - Is familiar with relevant technology at the same level as target users |
| 101 | |
| 102 | **Write a screener survey** (see `templates/screener-template.md`): |
| 103 | - Define specific behaviors you |