User Research
Plan interviews, usability tests, or surveys and turn raw notes into prioritized themes before you ship the wrong thing.
Overview
User Research is an agent skill most often used in Idea—audience (also Validate—prototype and scope) that plans, conducts, and synthesizes user studies via interviews, tests, and surveys.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill user-researchWhat is this skill?
- Comparison table for six research methods (interviews, usability, surveys, card sorting, diary studies, A/B) with sample
- Five-part interview guide structure with minute-by-minute timing (warm-up through wrap-up)
- Four analysis frameworks: affinity mapping, impact/effort matrix, journey mapping, and jobs to be done
- Actionable sample-size guidance (e.g. 5–8 for interviews/usability, 100+ for surveys, 15–30 for card sorting)
- End-to-end flow: plan studies, conduct sessions, and synthesize findings into prioritization inputs
- 6 research methods documented with sample sizes and typical timelines
- 5-section interview guide with per-section minute budgets
- 4 analysis frameworks: affinity mapping, impact/effort, journey mapping, jobs to be done
Adoption & trust: 2.1k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are building solo and do not know which research method, guide, or synthesis approach will turn scattered user conversations into decisions you can ship on.
Who is it for?
Founders and solo builders who have a hypothesis or early UI and need a lightweight, credible research plan without hiring a full UX team.
Skip if: Teams that already have signed-off quantitative evidence and only need implementation, or work that is purely technical with no human workflow to study.
When should I use this skill?
Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when you need help understanding users through research.
What do I get? / Deliverables
You leave with a chosen method, a timed interview or test plan, and a clear path to themed, prioritized findings you can fold into scope and prototype work.
- Research plan with method, sample size, and timeline
- Interview or usability session guide aligned to the five-part structure
- Synthesis output: themed findings with prioritization via impact/effort or JTBD framing
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Solo builders need to understand users before they over-build; this skill’s canonical shelf is early discovery, even though the same playbooks apply again during prototype validation. Audience work—needs, motivations, and workflows—maps directly to the audience subphase under Idea, where research questions and method choice matter most.
Where it fits
Draft a 5–8 participant interview guide to clarify who struggles with your problem and what they hire solutions to do today.
Pick interviews versus a 100+ response survey based on whether you need depth on motivations or counts on preferences.
Plan a one-to-two-week usability test with five timed tasks against a clickable onboarding flow.
Affinity-map session notes into themes and plot findings on an impact/effort matrix to trim the MVP backlog.
Run short win-back interviews after activation drops to map where the post-launch journey breaks.
How it compares
Use a structured research workflow instead of improvised customer chats that never become comparable themes or priorities.
Common Questions / FAQ
Who is user-research for?
It is for solo and indie builders using Claude Code, Cursor, Codex, or similar agents who need interview guides, usability plans, survey framing, and synthesis—not a dedicated researcher on payroll.
When should I use user-research?
Use it in Idea when defining audience and research questions; in Validate when planning usability tests or surveys against a prototype; and in Grow when re-interviewing users after launch to explain churn or confusion.
Is user-research safe to install?
Treat it as procedural guidance in your repo; review the Security Audits panel on this Prism page and your org policy before enabling skills from third-party plugin bundles.
SKILL.md
READMESKILL.md - User Research
# User Research Help plan, execute, and synthesize user research studies. ## Research Methods | Method | Best For | Sample Size | Time | |--------|----------|-------------|------| | User interviews | Deep understanding of needs and motivations | 5-8 | 2-4 weeks | | Usability testing | Evaluating a specific design or flow | 5-8 | 1-2 weeks | | Surveys | Quantifying attitudes and preferences | 100+ | 1-2 weeks | | Card sorting | Information architecture decisions | 15-30 | 1 week | | Diary studies | Understanding behavior over time | 10-15 | 2-8 weeks | | A/B testing | Comparing specific design choices | Statistical significance | 1-4 weeks | ## Interview Guide Structure 1. **Warm-up** (5 min): Build rapport, explain the session 2. **Context** (10 min): Understand their current workflow 3. **Deep dive** (20 min): Explore the specific topic 4. **Reaction** (10 min): Show concepts or prototypes 5. **Wrap-up** (5 min): Anything we missed? Thank them. ## Analysis Framework - **Affinity mapping**: Group observations into themes - **Impact/effort matrix**: Prioritize findings - **Journey mapping**: Visualize the user experience over time - **Jobs to be done**: Understand what users are hiring your product to do ## Deliverables - Research plan (objectives, methods, timeline, participants) - Interview guide (questions, probes, activities) - Synthesis report (themes, insights, recommendations) - Highlight reel (key quotes and observations)