research-users — Claude Code command: what it does, how to install
research-users synthesizes research notes, survey exports, and tickets into user personas, behavioral segments, and journey maps. Helpful for PMs evaluating qualitative data.
MIT ★ 28,211 updated 2026-10-16
/plugin marketplace add phuryn/pm-skills
/plugin install pm-market-research@pm-skillsWhat research-users does
The command processes raw feedback, survey spreadsheets, support tickets, or plain product descriptions. When you lack field data, it generates research-backed hypotheses instead of stalling.
Execution proceeds through defined phases. It identifies 3–4 personas using the JTBD framework via the user-personas skill, detailing goals and friction points. Next, it builds behavioral segments and maps the customer journey across onboarding, active use, and advocacy. The final deliverable is a formatted Markdown report with summary tables and suggested next steps.
Small datasets receive adjusted treatment. For instance, five interviews prompt the command to label findings as hypotheses rather than verified conclusions.
What it helps with
- synthesize messy interview notes and survey exports
- build JTBD-focused user personas with pain points
- create behavioral user segments tied to willingness to pay
- map customer journeys highlighting emotional friction points
Example prompts for the agent
- /research-users B2B project management tool for agencies — help me understand our users
- /research-users [paste NPS survey responses and customer feedback]
- /research-users [upload customer interview transcripts and support tickets]
How to install research-users
1Plugin marketplace
/plugin marketplace add phuryn/pm-skills/plugin install pm-market-research@pm-skills2Manually: put the files in place
.claude/commands/research-users.mdCall it with /research-users. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/research-users.mdCall it with /prompts:research-users. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/research-users.prompt.mdManually: put the files in place
.gemini/commands/research-users.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about research-users
How to install research-users in Claude Code?
Add the marketplace via /plugin marketplace add phuryn/pm-skills and then install the plugin with /plugin install pm-market-research@pm-skills.
What does research-users do?
It turns raw feedback or survey logs into actionable personas, behavioral market segments, and an end-to-end customer journey map saved as a Markdown report.
Can I run research-users without survey data or interview notes?
Yes. You can provide a brief product description, and the command will draft exploratory hypotheses with instructions on how to test them.
Source text
research-users.md · MIT
--- description: Comprehensive user research — build personas, segment users, and map the customer journey from research data argument-hint: "<research data, survey results, or product description>" --- # /research-users -- User Research Synthesis Turn raw research data into actionable user personas, behavioral segments, and customer journey maps. Accepts survey data, interview notes, feedback, analytics, or a product description for exploratory research. ## Invocation ``` /research-users [upload survey results, interview notes, or feedback data] /research-users B2B project management tool for agencies — help me understand our users /research-users [paste user feedback or support ticket data] ``` ## Workflow ### Step 1: Accept Research Inputs Accept from any combination: - Survey responses (CSV, spreadsheet, pasted) - Interview notes or transcripts - Support tickets or feature requests - Product analytics / behavioral data - NPS or satisfaction data - Product description (for exploratory research without data) Ask: - What research do you have? What format? - What do you want to understand? (who are our users, how do they differ, where's the friction) - What decisions will this inform? (roadmap, positioning, pricing, onboarding) ### Step 2: Build Personas Apply the **user-personas** skill: - Identify 3-4 distinct personas from the data - For each persona: name, role, goals (JTBD), pains, gains, behavioral patterns - Include unexpected insights — things that surprised you in the data - Note persona prevalence (what % of your base each represents, if data allows) ### Step 3: Segment Users Apply the **user-segmentation** and **market-segments** skills: - Create behavioral segments (not just demographics) - For each segment: size, JTBD, product fit, willingness to pay, engagement level - Identify the highest-value segment and the highest-growth segment - Map segments to personas (how they overlap) ### Step 4: Map the Customer Journey Apply the **customer-journey-map** skill: - Map the end-to-end journey: Awareness → Consideration → Onboarding → Active Use → Expansion → Advocacy - For each stage: touchpoints, emotions, pain points, aha moments - Identify the biggest drop-off points - Highlight moments of delight worth amplifying ### Step 5: Generate Research Report ``` ## User Research Report: [Product] **Date**: [today] **Data sources**: [what was analyzed] **Sample size**: [if applicable] ### Executive Summary [3-5 sentences: key findings and implications] ### Personas #### Persona 1: [Name] — "[Quote that captures them]" - **Who**: [role, context, experience level] - **Primary JTBD**: [When..., I want to..., so I can...] - **Key pains**: [top 3] - **Key gains**: [what delights them] - **Behavioral pattern**: [how they use the product] - **Prevalence**: [X% of user base] [Repeat for each persona] ### User Segments | Segment | Size | Primary JTBD | Product Fit | Value | Growth | |---------|------|-------------|-------------|-------|--------| ### Customer Journey Map | Stage | Touchpoints | Emotion | Pain Points | Opportunities | |-------|------------|---------|-------------|---------------| ### Key Insights 1. [Insight with supporting evidence] 2. ... ### Recommendations 1. [Actionable recommendation tied to findings] 2. ... ### Open Questions [What the data didn't answer — suggested follow-up research] ``` Save as markdown. ### Step 6: Offer Next Steps - "Want me to **create interview scripts** to go deeper on a specific persona?" - "Should I **analyze sentiment** across these segments?" - "Want me to **build a value proposition** for the top persona?" - "Should I **prioritize the journey map pain points** as feature opportunities?" ## Notes - If data is thin, be transparent about confidence levels — 5 interviews → hypotheses, not conclusions - Personas should be useful, not decorative — every persona should influence a product decision - Behavioral segments are more actionable than demographic segments for product decisions - The journey map should surface emotions, not just actions — where users feel frustrated vs. delighted drives prioritization - If no data is provided, generate research-informed hypotheses and recommend how to validate them
© Paweł Huryn · MIT · phuryn/pm-skills