Synthesize Research
Turn interview notes, surveys, support tickets, and analytics into ranked themes and roadmap-ready recommendations.
Overview
Synthesize Research is an agent skill most often used in Idea (also Validate and Grow) that turns interviews, surveys, and feedback into ranked themes and roadmap recommendations.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill synthesize-researchWhat is this skill?
- Multi-source intake: pasted notes, uploads, knowledge base, user feedback, product analytics, meeting transcription
- Workflow starts with clarifying research type and source count before synthesis
- Designed to extract themes and rank findings by frequency and impact
- Outputs structured insights aimed at roadmap recommendations
- Slash command entry: /synthesize-research with topic or question argument
- 6 optional connector source families listed in gather step
Adoption & trust: 1.6k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have interview notes, survey rows, and tickets but no structured view of which themes matter most for the roadmap.
Who is it for?
Founders and indie PMs drowning in qualitative research who need one structured synthesis pass before committing to features.
Skip if: Situations where discovery is finished, insights are already prioritized in a spec, and you only need implementation or code review.
When should I use this skill?
When you have interview notes, survey responses, or support tickets to make sense of, need themes ranked by frequency and impact, or want raw feedback turned into roadmap recommendations; also via /synthesize-research wi
What do I get? / Deliverables
You get clustered insights ranked by frequency and impact plus recommendations you can feed into scoping and prioritization conversations.
- Structured insight summary with themes
- Frequency- and impact-ranked findings
- Roadmap-oriented recommendations
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Idea/research because the skill’s core job is making sense of raw qualitative and quantitative inputs before you lock scope. Research subphase matches gathering from interviews, surveys, usability tests, and connected feedback or analytics sources.
Where it fits
Cluster ten customer interview transcripts into top jobs-to-be-done before picking a niche.
Rank survey and usability findings to decide which MVP features survive a two-week build.
Synthesize recent tickets and feature requests to spot the highest-frequency churn drivers.
Combine sales call notes with analytics funnel drops to articulate who struggles and why.
How it compares
Research synthesis workflow across pasted sources and optional connectors—not a single-source survey dashboard or generic note summarizer.
Common Questions / FAQ
Who is synthesize-research for?
Solo builders and small teams doing customer discovery who collect interviews, surveys, usability tests, tickets, or analytics and need themes tied to product decisions.
When should I use synthesize-research?
In Idea/research when consolidating discovery; in Validate/scope when choosing MVP cuts from evidence; in Grow/support when mining tickets and feedback for recurring pain.
Is synthesize-research safe to install?
Review the Security Audits panel on this page before connecting knowledge base, feedback, analytics, or transcription tools that may access customer data.
SKILL.md
READMESKILL.md - Synthesize Research
# Synthesize Research > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Synthesize user research from multiple sources into structured insights and recommendations. ## Usage ``` /synthesize-research $ARGUMENTS ``` ## Workflow ### 1. Gather Research Inputs Accept research from any combination of: - **Pasted text**: Interview notes, transcripts, survey responses, feedback - **Uploaded files**: Research documents, spreadsheets, recordings summaries - **~~knowledge base** (if connected): Search for research documents, interview notes, survey results - **~~user feedback** (if connected): Pull recent support tickets, feature requests, bug reports - **~~product analytics** (if connected): Pull usage data, funnel metrics, behavioral data - **~~meeting transcription** (if connected): Pull interview recordings, meeting summaries, and discussion notes Ask the user what they have: - What type of research? (interviews, surveys, usability tests, analytics, support tickets, sales call notes) - How many sources / participants? - Is there a specific question or hypothesis they are investigating? - What decisions will this research inform? ### 2. Process the Research For each source, extract: - **Key observations**: What did users say, do, or experience? - **Quotes**: Verbatim quotes that illustrate important points - **Behaviors**: What users actually did (vs what they said they do) - **Pain points**: Frustrations, workarounds, and unmet needs - **Positive signals**: What works well, moments of delight - **Context**: User segment, use case, experience level ### 3. Identify Themes and Patterns Apply thematic analysis — see **Research Synthesis Methodology** below for detailed guidance on thematic analysis, affinity mapping, and triangulation techniques. Group observations into themes, count frequency across participants, and assess impact severity. Note contradictions and surprises. Create a priority matrix: - **High frequency + High impact**: Top priority findings - **Low frequency + High impact**: Important for specific segments - **High frequency + Low impact**: Quality-of-life improvements - **Low frequency + Low impact**: Note but deprioritize ### 4. Generate the Synthesis Produce a structured research synthesis: #### Research Overview - Methodology: what types of research, how many participants/sources - Research question(s): what we set out to learn - Timeframe: when the research was conducted #### Key Findings For each major finding (aim for 5-8): - **Finding statement**: One clear sentence describing the insight - **Evidence**: Supporting quotes, data points, or observations (with source attribution) - **Frequency**: How many participants/sources support this finding - **Impact**: How significantly this affects the user experience or business - **Confidence level**: High (strong evidence), Medium (suggestive), Low (early signal) Order findings by priority (frequency x impact). #### User Segments / Personas If the research reveals distinct user segments: - Segment name and description - Key characteristics and behaviors - Unique needs and pain points - Size estimate if data is available #### Opportunity Areas Based on the findings, identify opportunity areas: - What user needs are unmet or underserved - Where do current solutions fall short - What new capabilities would unlock value - Prioritized by potential impact #### Recommendations Specific, actionable recommendations: - What to build, change, or investigate further - Tied back to specif