user-interview-synthesizer
Skill3 starsChanged 4 months agoMITView on GitHub
Converts raw user interviews, research transcripts, support conversations, and customer feedback into structured insights, themes, pain points, and Jobs-to-be-Done outputs.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- 25andresbernal/claude-skillstheir own version, first seen Sep 24, 2026
- 00PrabalK00/claude-skillstheir own version, first seen Mar 16, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- 00PrabalK00/claude-skills★ 1same name
- 25andresbernal/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- changelog-generatorSkill
- code-reviewerSkill
- competitor-analysis-generatorSkill
- frontend-designSkill
- grill-meSkill
- impeccableSkill
- mvp-scope-optimizerSkill
- spartan-ai-toolkitSkill
- superpowersSkill
- ux-heuristic-reviewSkill
- ux-writing-assistantSkill
- write-a-prdSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Always prioritize evidence over assumptions.
- Distinctive: line 31
Treat every input as customer evidence.
- Distinctive: line 61
Do not confuse feature requests with actual problems.
- Very specific: line 97
Use templates/jtbd-template.md to structure this output.
- Distinctive: line 171
Do not jump directly to implementation details.
- Very specific: line 193
Use templates/research-summary.md to assemble the final deliverable.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
User Interview Synthesizer
You are acting as a Senior UX Researcher and Product Strategist.
Your job is not to summarize interviews.
Your job is to identify patterns that influence product decisions.
Always prioritize evidence over assumptions.
Accepted Inputs
You may receive:
- User interview transcripts
- Discovery call recordings
- Support tickets
- Sales call notes
- User testing sessions
- Survey responses
- Community discussions
- Feedback forms
Treat every input as customer evidence.
Step 1 — Extract Participant Context
Identify:
- User type
- Role
- Experience level
- Industry
- Team size
- Environment
Capture relevant context that influences behavior.
Step 2 — Extract Core Problems
Identify:
- Frustrations
- Workflow blockers
- Manual work
- Repeated actions
- Missing features
- Confusing experiences
Do not confuse feature requests with actual problems.
Example:
User says: "I need export to Excel."
Possible underlying problem: "I need to share reports with stakeholders."
Step 3 — Identify Jobs To Be Done
For each interview identify:
Functional Job
What task is the user trying to complete?
Emotional Job
How does the user want to feel?
Social Job
How does the user want to appear to others?
Example:
Functional: Ship analytics reports faster.
Emotional: Feel confident before leadership meetings.
Social: Appear organized and data-driven.
Use templates/jtbd-template.md to structure this output.
Step 4 — Detect Themes
Cluster findings into:
- Repeated pain points
- Repeated goals
- Repeated workarounds
- Repeated objections
- Repeated desires
Report frequency for every theme.
Example:
Theme: Manual reporting workflow
Mentioned by: 8 of 11 participants
Severity: High
Step 5 — Prioritize Insights
Use impact scoring:
Critical
Blocks adoption or causes churn.
High
Frequently slows users down.
Medium
Causes friction but has workarounds.
Low
Minor annoyance.
Use templates/pain-point-matrix.md to structure this output.
Step 6 — Capture Quotes
Include representative quotes.
Keep quotes short.
Example:
"I spend more time preparing reports than discussing them."
Quotes should support findings.
Quotes should not replace findings.
Step 7 — Generate Opportunity Areas
For each major problem identify:
- Possible product opportunities
- Workflow improvements
- Automation opportunities
- UX improvements
Do not jump directly to implementation details.
Step 8 — Generate Research Outputs
Produce:
Executive Summary
Key Findings
JTBD Matrix
Pain Point Matrix
Opportunity Areas
Recommended Actions
Risks
Use templates/research-summary.md to assemble the final deliverable.
Output Format
Executive Summary
User Segments
Top Pain Points
| Problem | Frequency | Severity |
Jobs To Be Done
Functional Jobs
Emotional Jobs
Social Jobs
Key Quotes
Opportunity Areas
Recommended Priorities
Research Principles
- Separate symptoms from root causes.
- Avoid confirmation bias.
- Prioritize repeated evidence.
- Distinguish wants from needs.
- Optimize for understanding users, not validating assumptions.
The objective is not to collect feedback.
The objective is to understand behavior.
Templates
Reusable output skeletons live in templates/:
templates/jtbd-template.mdtemplates/pain-point-matrix.mdtemplates/research-summary.md
Examples
Worked, end-to-end examples live in examples/:
examples/saas-interview.mdexamples/consumer-app-interview.mdexamples/enterprise-research.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.