research-synthesis
anthropics/knowledge-work-plugins
Distill interview transcripts, surveys, and feedback into themes, insights, and prioritized recommendations.
What is research-synthesis?
Synthesizes qualitative research data—interviews, surveys, usability tests, support tickets, and reviews—into structured themes, user segments, and actionable recommendations. Use this when you have raw research data that needs to be analyzed for patterns and strategic direction.
- Identifies recurring themes across research participants with prevalence counts and supporting quotes
- Extracts user segments with characteristics, needs, and estimated size
- Maps insights to opportunities with impact and effort assessment
- Generates prioritized recommendations grounded in research findings
- Surfaces questions for further research based on gaps in current data
- Validates qualitative findings against behavioral metrics if product analytics is connected
How to install research-synthesis
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill research-synthesisHow to use research-synthesis
- 1.Gather your research data (transcripts, survey results, test notes, or feedback) in text or CSV format
- 2.Invoke /research-synthesis with your data as the argument
- 3.Review the generated synthesis for themes, segments, and recommendations
- 4.Cross-reference quotes and prevalence counts to validate findings
- 5.Use the Insights → Opportunities table to prioritize next steps
- 6.Reference the Methodology Notes section to document any research limitations
Use cases
- Analyze 10+ interview transcripts to identify pain points and feature opportunities for product roadmap planning
- Synthesize NPS and CSAT survey responses to understand customer satisfaction drivers and detractors
- Review usability test notes from 5-8 participants to pinpoint UX friction and design improvements
- Consolidate support tickets and feature requests to prioritize bug fixes and enhancements
- Extract themes from app store reviews to identify common user complaints and praise
- Product managers planning roadmaps based on user feedback
- UX researchers synthesizing qualitative studies
- Customer success teams analyzing support patterns
- Product teams conducting voice-of-customer research
- Design teams using research to inform iteration
research-synthesis FAQ
Paste interview transcripts, survey results (CSV or text), usability test notes, support tickets, or feedback directly. The skill accepts raw text, structured data, or mixed formats.
The skill works with any sample size, but findings are more robust with 5+ participants for interviews or usability tests. Larger survey samples (50+) provide better statistical grounding.
Yes. You can mix interview transcripts, survey data, and support tickets in a single request. The skill will identify themes across all sources and note the method distribution.
The skill captures prevalence (e.g., '5 of 8 users') and includes direct quotes, so you can see where disagreement exists. Use the Methodology Notes to flag areas needing further research.
The skill references the user-research skill for research methods and frameworks. If product analytics or knowledge base connectors are available, it can validate findings against usage data and compare against prior studies.
Full instructions (SKILL.md)
Source of truth, from anthropics/knowledge-work-plugins.
name: research-synthesis description: Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses that need to be distilled into patterns, user segments, and prioritized next steps. argument-hint: "<research data, transcripts, or survey results>"
/research-synthesis
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Synthesize user research data into actionable insights. See the user-research skill for research methods, interview guides, and analysis frameworks.
Usage
/research-synthesis $ARGUMENTS
What I Accept
- Interview transcripts or notes
- Survey results (CSV, pasted data)
- Usability test recordings or notes
- Support tickets or feedback
- NPS/CSAT responses
- App store reviews
Output
## Research Synthesis: [Study Name]
**Method:** [Interviews / Survey / Usability Test] | **Participants:** [X]
**Date:** [Date range] | **Researcher:** [Name]
### Executive Summary
[3-4 sentence overview of key findings]
### Key Themes
#### Theme 1: [Name]
**Prevalence:** [X of Y participants]
**Summary:** [What this theme is about]
**Supporting Evidence:**
- "[Quote]" — P[X]
- "[Quote]" — P[X]
**Implication:** [What this means for the product]
#### Theme 2: [Name]
[Same format]
### Insights → Opportunities
| Insight | Opportunity | Impact | Effort |
|---------|-------------|--------|--------|
| [What we learned] | [What we could do] | High/Med/Low | High/Med/Low |
### User Segments Identified
| Segment | Characteristics | Needs | Size |
|---------|----------------|-------|------|
| [Name] | [Description] | [Key needs] | [Rough %] |
### Recommendations
1. **[High priority]** — [Why, based on which findings]
2. **[Medium priority]** — [Why]
3. **[Lower priority]** — [Why]
### Questions for Further Research
- [What we still don't know]
### Methodology Notes
[How the research was conducted, any limitations or biases to note]
If Connectors Available
If ~~user feedback is connected:
- Pull support tickets, feature requests, and NPS responses to supplement research data
- Cross-reference themes with real user complaints and requests
If ~~product analytics is connected:
- Validate qualitative findings with usage data and behavioral metrics
- Quantify the impact of identified pain points
If ~~knowledge base is connected:
- Search for prior research studies and findings to compare against
- Publish the synthesis to your research repository
Tips
- Include raw quotes — Direct participant quotes make insights credible and memorable.
- Separate observations from interpretations — "5 of 8 users clicked the wrong button" is an observation. "The button placement is confusing" is an interpretation.
- Quantify where possible — "Most users" is vague. "7 of 10 users" is specific.
Related skills
More from anthropics/knowledge-work-plugins and the wider catalog.

review-contract
Review contracts against your organization's playbook—flag deviations, generate redlines, and analyze business impact.

risk-assessment
Systematically identify, assess, and mitigate operational risks across projects, vendors, and decisions.

rivet-sdk
Reference skill for Zoom Rivet SDK. Use after routing to a Rivet-based server workflow when implementing auth handling, webhook consumers, API wrappers, multi-module composition, or Lambda receiver patterns.

roadmap-update
Update, create, or reprioritize your product roadmap with structured frameworks and dependency tracking.

run-campaign
Runs an end-to-end marketing campaign — sales analysis, content brief, Canva assets, HubSpot send. Accepts optional lookback and channel arguments.

runbook
Create step-by-step operational runbooks to turn tribal knowledge into repeatable procedures with troubleshooting and escalation paths.