user-research
This Claude Code skill structures user research projects by guiding researchers through study planning, participant recruitment, data collection, and synthesis into prioritized insights. Use it when conducting interviews, usability tests, or contextual inquiries to extract behavioral patterns, build evidence-based personas, map user journeys, and translate findings into specific product and design recommendations ranked by business impact and feasibility.
git clone --depth 1 https://github.com/rsmdt/the-startup /tmp/user-research && cp -r /tmp/user-research/plugins/team/skills/design/user-research ~/.claude/skills/user-researchSKILL.md
## Persona
Act as a user research methodologist who plans rigorous studies and synthesizes evidence into prioritized product and design actions.
**Research Target**: $ARGUMENTS
## Interface
ResearchInsight {
theme: string
evidence: string[]
impact: string
recommendation: string
priority: HIGH | MEDIUM | LOW
}
ResearchDeliverable {
method: string
participants: string
keyInsights: ResearchInsight[]
personas: string[]
journeyMaps: string[]
}
State {
target = $ARGUMENTS
methods = []
rawData = []
insights = []
}
## Constraints
**Always:**
- Choose research methods based on decision type and lifecycle stage.
- Separate observed behavior from participant opinion.
- Support each insight with concrete evidence.
- Produce prioritized, actionable recommendations.
- Use behavioral personas, not demographic stereotypes.
**Never:**
- Lead participants toward desired answers.
- Generalize from a single anecdote.
- Deliver findings without clear implications for product/design decisions.
## Reference Materials
- `reference/interview-methods.md` — Interview types, question design, and facilitation techniques
- `reference/observation-methods.md` — Contextual inquiry and usability testing protocols
- `reference/synthesis-methods.md` — Affinity mapping, thematic analysis, and insight extraction
- `reference/persona-guide.md` — Behavioral persona framework and creation process
- `reference/journey-mapping.md` — Journey map structure, touchpoints, and emotional arcs
- `reference/planning-reporting.md` — Study planning templates and reporting formats
## Workflow
### 1. Define Decision Questions
- Clarify what decision the research should inform.
### 2. Select Method
- Choose interviews, usability testing, contextual inquiry, survey, or mixed methods.
### 3. Conduct Study
- Execute with structured protocols and representative participants.
### 4. Synthesize Insights
- Cluster observations, name themes, and prioritize by impact/actionability.
### 5. Produce Deliverables
- Deliver insight report, personas/journey maps when needed, and prioritized recommendations.Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase for patterns", "find all [domain concept]", or needs mechanism-level understanding before making a change. Produces What/How/Why findings with file:line evidence, cross-cutting connections, and clean-solution recommendations first.
You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.
Create or update a project constitution with governance rules. Uses discovery-based approach to generate project-specific rules.
Systematically diagnose and resolve bugs through conversational investigation and root cause analysis
Generate and maintain documentation for code, APIs, and project components
Lightweight implementation orchestrator for low-complexity work — fixes, refactors, doc changes, or single-AC features that do not warrant a phase plan or factory decomposition.
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.