agentleFS
nisarthnisarth/claude-skills-store/skills/design/user-research/SKILL.md

user-research

Skill1 starsChanged 7 months agoMITView on GitHub

Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research. Trigger phrases: "user research plan", "interview guide", "usability test plan", "survey design", "research questions", "plan user interviews", "test this with users", "research methodology", "recruitment screener", "moderation guide"

18 other projects use a version of this, 5 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use prd-writer and competitive-analysis.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nimbalystSkill

    prd-writer

    Create structured Product Requirements Documents (PRDs) with prioritized requirements. Use when writing product specs, feature requirements, or project briefs.

    Also in 3 projects that use this

  • AnthropicSkill

    competitive-analysis

    Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user cannot articulate the decision this research informs, help them clarify before designing the study.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

User Research Planning

Plan and structure user research: define research questions, choose methods, design interview guides, create usability test plans, draft surveys, and write recruitment screeners.

Workflow

Step 1: Define the Research Objective

Clarify what you need to learn:

### Research Brief

**Business question**: [What decision will this research inform?]
**Research question**: [What do we need to learn from users?]
**Hypothesis**: [What do we currently believe? What assumptions are we testing?]
**Decision**: [What will we do differently based on the results?]
**Timeline**: [When do we need answers?]
**Stakeholders**: [Who will use these findings?]

If the user cannot articulate the decision this research informs, help them clarify before designing the study. Research without a decision to inform is academic, not actionable.

Step 2: Choose the Method

MethodBest ForParticipantsTime
User interviewsUnderstanding motivations, pain points, mental models5-82-3 weeks
Usability testingEvaluating a specific design or prototype5-81-2 weeks
SurveyQuantifying behaviors, preferences, satisfaction100+1-2 weeks
Card sortingInformation architecture, navigation structure15-301 week
Diary studyUnderstanding behavior over time10-152-4 weeks
A/B testComparing two specific options at scale1000+1-4 weeks
Contextual inquiryObserving behavior in natural environment5-82-3 weeks
Concept testingValidating early ideas before building8-121-2 weeks

Selection criteria:

  • Exploratory (understand the problem): Interviews, contextual inquiry, diary study
  • Evaluative (test a solution): Usability testing, A/B test
  • Generative (discover opportunities): Interviews, contextual inquiry
  • Quantitative validation: Surveys, A/B tests, analytics

Step 3: Design the Research Plan

### Research Plan: [Study Name]

**Objective**: [What we will learn]
**Method**: [Selected method]
**Participants**: [Number, segment, criteria]
**Timeline**: [Key dates]
**Deliverables**: [What the output will be]

#### Recruitment
**Target profile**:
- [Criterion 1]: [Requirement]
- [Criterion 2]: [Requirement]
- [Exclusion]: [Who to exclude]

**Screener questions**:
1. [Question to qualify participants]
2. [Question to qualify participants]
3. [Question to ensure diversity]

**Incentive**: [Amount and form]

#### Session Structure
- **Duration**: [Minutes]
- **Format**: [Remote/in-person, moderated/unmoderated]
- **Tools**: [Platform, recording, note-taking]

#### Discussion Guide / Test Plan
[See Step 4]

#### Analysis Plan
- **Method**: [Thematic analysis, task success rates, etc.]
- **Output**: [Synthesis report, recommendations, presentation]

Step 4: Create Research Instruments

Interview Guide

### Interview Guide: [Topic]
Duration: [X] minutes

**Introduction** (5 min)
- Thank participant, explain purpose
- Confirm recording consent
- "There are no right or wrong answers. We want to hear about your experience."

**Warm-up** (5 min)
- Tell me about your role and what a typical day looks like.
- How do you currently handle [topic]?

**Core Questions** (30 min)
1. [Open-ended question about behavior]
   - Follow-up: Can you walk me through the last time you did that?
   - Probe: What was the hardest part?

2. [Open-ended question about pain points]
   - Follow-up: How do you work around that?
   - Probe: How often does this happen?

3. [Open-ended question about needs]
   - Follow-up: What would an ideal solution look like?
   - Probe: What have you tried before?

**Wrap-up** (5 min)
- Is there anything I did not ask about that you think is important?
- Would you be open to a follow-up session?

Usability Test Plan

Structure each task with: scenario (realistic user goal), success criteria, metrics (completion, time, errors, satisfaction), and moderator observation notes. Include post-task questions:

  • How easy or difficult was that? (1-5 scale)
  • What would you expect to happen next?
  • Was anything confusing?

Include post-session questions about overall experience and comparison to current tools.

Survey Design

Structure surveys with: estimated completion time, sections by topic, a mix of closed-ended questions (single select, multi-select, Likert scales) and open-ended follow-ups. Example question types:

  1. [Closed-ended question] (Single select / Multi-select / Likert)
    • Option A
    • Option B
    • Option C
    • Other (specify)
  2. [Rating scale question] (1-5 or 1-7) Strongly disagree ... Strongly agree
  3. [Open-ended follow-up] "Please explain your answer."

### Step 5: Prepare for Execution

Checklist before starting:
- [ ] Research plan reviewed by stakeholders
- [ ] Recruitment screener distributed
- [ ] Participants scheduled with calendar invites
- [ ] Recording consent forms prepared
- [ ] Discussion guide or test plan piloted (run 1 practice session)
- [ ] Note-taking template ready
- [ ] Observer guide distributed (if others are watching)

## Examples

### Example 1: Interview Planning
**User**: "Plan user interviews about our search experience."
**Response**: Define the research question (how do users search, what frustrates them, what would improve their experience). Design a 45-minute interview guide with warm-up, behavior questions, pain point exploration, and ideal-state questions. Write a recruitment screener targeting users who search frequently.

### Example 2: Usability Test
**User**: "Create a usability test plan for our new checkout flow."
**Response**: Define 4-5 realistic tasks (add item, apply coupon, change shipping, complete purchase). Write natural scenarios. Set success criteria for each. Include post-task satisfaction ratings and a System Usability Scale at the end. Plan for 6 sessions over 3 days.

### Example 3: Survey Design
**User**: "Design a survey to understand why users churn."
**Response**: Structure with segments: usage frequency, satisfaction by feature area, reason for leaving (multiple choice + open-ended), likelihood to return, competitive alternatives used. Keep to 10-12 questions. Include logic branching based on churn reason. Target recent churners within 30 days.

## Best Practices

1. **Ask about behavior, not preferences.** "Tell me about the last time you did X" reveals more than "Would you like feature Y?" People are bad at predicting their own behavior.
2. **Do not lead the witness.** "Was that confusing?" leads to "yes." "How would you describe that experience?" lets the participant choose their own words.
3. **Five participants find 80% of usability issues.** For qualitative studies, 5-8 participants per segment is sufficient. More participants have diminishing returns.
4. **Pilot everything.** Run one test session before the real ones. You will find questions that are confusing, tasks that are too easy, or timing that is off.
5. **Separate research from design solutioning.** Research tells you what the problem is. Do not jump to solutions during the interview.
6. **Record with consent.** Recordings let you revisit exact quotes and share with stakeholders who were not present. Always get explicit consent.
7. **Debrief immediately after each session.** Capture top observations while they are fresh. Do not wait until all sessions are done.
8. **Share findings, not just reports.** Invite stakeholders to observe sessions. Seeing a user struggle is more persuasive than reading about it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.