mcpbeat

User Research

nicepkg/user-research

User research methods, customer insight gathering, and problem validation for product discovery.

3k tokens
context cost
the whole folder, loaded on every use
6
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
275
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/nicepkg/ai-workflow --skill user-research

The instruction itself

18 sections, as written by the author

User Research Skill

Conduct effective user research to understand customer needs, behaviors, and pain points. Master interview techniques and insight synthesis.

Research Methods

Method Selection Guide

| Method | When | Sample | Duration |

|--------|------|--------|----------|

| Interviews | Deep understanding | 15-25 | 45-60 min |

| Surveys | Quantitative validation | 100+ | 5-10 min |

| Usability | UX issues | 5-8 | 30-60 min |

| Observation | Real behavior | 3-5 | 2-4 hours |

| Analytics | Scale patterns | All users | Ongoing |

Qualitative Research

Interview Structure

OPENING (5 min):
- Intro & rapport
- Permission to record
- Context setting

CONTEXT (10 min):
- Role and responsibilities
- Day-to-day workflow
- Tools used

DEEP DIVE (20 min):
- "Walk me through [process]..."
- "Tell me about last time [problem]..."
- "What frustrates you most?"

IMPACT (10 min):
- "What happens when [problem]?"
- "How much time/money does it cost?"

FUTURE (10 min):
- "What would ideal look like?"
- "What would you pay for [solution]?"

CLOSING (5 min):
- "Anything else?"
- "Can I follow up?"

Interview Best Practices

  • Listen 70%, talk 30%
  • Ask "Why?" 5 times
  • Avoid leading questions
  • Use silence effectively
  • Capture quotes verbatim

Quantitative Research

Survey Design

Question Types:

  • Rating scale (1-5, 1-10)
  • Multiple choice
  • Open-ended (limit 1-2)
  • Ranking

NPS Question:

"How likely are you to recommend [product] to a friend? (0-10)"

Sample Size Calculator

For 95% confidence, 5% margin:
- Population 100 → Sample 80
- Population 500 → Sample 217
- Population 1000 → Sample 278
- Population 10000 → Sample 370

Synthesis

Affinity Mapping

  • Write each insight on sticky note
  • Group similar insights
  • Name each group (theme)
  • Rank by frequency/impact
  • Extract top 5-10 themes

Persona Template

NAME: [Descriptive name]
ROLE: [Job title, company type]
QUOTE: "[Real quote from research]"

GOALS:
- [Goal 1]
- [Goal 2]

FRUSTRATIONS:
- [Pain 1]
- [Pain 2]

BEHAVIORS:
- [How they work]
- [Tools they use]

NEEDS:
- [Need 1]
- [Need 2]

Journey Map

| Stage | Actions | Emotions | Pain Points | Opportunities |

|-------|---------|----------|-------------|---------------|

| Aware | Search | Curious | Hard to find | SEO, content |

| Consider | Compare | Confused | Too many options | Comparison |

| Purchase | Buy | Anxious | Complex checkout | Simplify |

| Use | Onboard | Overwhelmed | Steep learning | Better UX |

Troubleshooting

Yaygın Hatalar & Çözümler

| Hata | Olası Sebep | Çözüm |

|------|-------------|-------|

| Low response | Wrong incentive | $50-100 gift card |

| Surface insights | Leading questions | "Why?" 5x |

| Conflicting data | Mixed segments | Segment analysis |

| No show | Scheduling issues | Calendar hold, reminder |

Debug Checklist

[ ] Research plan documented mi?
[ ] Sample size sufficient mi?
[ ] Questions non-leading mi?
[ ] Recording consent alındı mı?
[ ] Synthesis done within 24h mi?
[ ] Insights actionable mi?

Recovery Procedures

  • Low Participation → Increase incentive, new channels
  • Conflicting Data → Segment by user type
  • Shallow Insights → Follow-up interviews

Learning Outcomes

  • Plan effective research studies
  • Conduct insightful interviews
  • Design valid surveys
  • Synthesize research data
  • Present actionable insights

How to use it

Copy the folder

Take nicepkg/user-research from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.