User Research
A comprehensive skill for user research — covering research methods, interview techniques, participant recruitment, synthesis, insight generation, readout formats, and continuous discovery habits. From early generative research to evaluative usability testing.
Profile →npx skills add cosmicstack-labs/mercury-agent-skills --skill user-research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill instructs an agent to apply comprehensive user research practices across generative and evaluative phases, including designing interviews, contextual inquiry plans, participant recruitment via screener logic, and synthesis techniques like affinity mapping. It covers defining research methods, structuring interviews (structured and semi-structured), planning contextual inquiries, recruitment logistics, incentive guidelines, sample sizing rules, and initial synthesis workflows (affinity mapping) with example data structures and templates. The agent is directed to generate interview guides, plan observation sessions, manage recruitment data models, and support data organization for insights and readouts.
How it works
- Emphasizes action-oriented research: end deliverables should include actionable recommendations.
- Distinguishes generative vs. evaluative research and qualitative vs. quantitative methods, and advises when to use each.
- Provides interview techniques, including structured and semi-structured formats, with stepwise structures and probing techniques.
- Includes templates and code-like scaffolds for interview guides, contextual inquiry plans, and screener data models; these templates define metadata, sections, durations, questions, and probes.
- Specifies recruitment logistics: screener design principles, incentive tables by participant type, and sample size guidelines per method.
- Describes synthesis workflows, notably affinity mapping with capture, cluster, label, and prioritize steps, plus example tooling.
When to use it
Use this skill for end-to-end user research programs from early discovery to usability evaluation, including planning studies, recruiting participants, conducting interviews and contextual inquiries, synthesizing findings, and preparing readouts. It is applicable when you need structured guidance on research design, participant engagement, and data organization throughout the research lifecycle.
What it can touch
- Tools declared: claude-code
- It includes code blocks and Python-like templates for interview guide generation, contextual inquiry plans, and screener data models. It references tools for visualization and collaboration (e.g., Miro, FigJam, MURAL) in the affinity mapping section.
Caveats
- The skill presents templates and example code but does not guarantee study outcomes or recruitment success.
- It covers biases and quality considerations, but practitioners should adapt to their context and ethics approvals where required.
- License: MIT
# User Research ## Core Principles Great user research produces not just data, but decision-grade insights. These principles underpin every effective research practice: 1. **Research without action is entertainment.** Every study should end with a clear "so what" — actionable recommendations that change what you build or how you build it. 2. **Bias is always present.** The best you can do is name it, design around it, and account for it in your analysis. Common biases: confirmation bias, interviewer bias, selection bias, social desirability bias. 3. **Quality over quantity.** Five well-recruited, well-moderated interviews produce more insight than fifty poorly run surveys. Depth beats breadth for generative work. 4. **Triangulate methods.** No single method tells the whole story. Combine qualitative (what people say/do) with quantitative (how many, how often) for robust insights. 5. **Participant comfort is paramount.** Research participants are giving you their time, attention, and vulnerability. Respect that. Make them feel safe, valued, and heard. 6. **Share raw data, not just summaries.** Teams make better decisions when they can watch recordings, read transcripts, and see patt
- Core Principles
- Research Maturity Model
- Research Methods
- Generative vs. Evaluative Research
- Qualitative vs. Quantitative Research
- Method Selection Matrix
- Interview Techniques
- Structured Interviews
- Semi-Structured Interviews
- Contextual Inquiry
- Recruitment
- Screening
- Incentives
- Sample Size
What does the User Research skill do?
A comprehensive skill for user research — covering research methods, interview techniques, participant recruitment, synthesis, insight generation, readout formats, and continuous discovery habits. From early generative research to evaluative usability testing.
How do I install it?
Run `npx skills add cosmicstack-labs/mercury-agent-skills --skill user-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From cosmicstack-labs/mercury-agent-skills, a repository with 364 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.