research-synthesis
$
npx mdskill add anthropics/knowledge-work-plugins/research-synthesisSynthesizes user research data into themes, insights, and prioritized recommendations.
- Helps distill patterns from transcripts, surveys, and feedback into actionable findings.
- Integrates with tools for handling CSV data, notes, and recordings as input sources.
- Decides recommendations by analyzing prevalence, evidence, and impact of identified themes.
- Presents results in a structured markdown format with summaries, themes, and opportunities.
SKILL.md
.github/skills/research-synthesisView on GitHub ↗
--- 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](../../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 ```markdown ## 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 1. **Include raw quotes** — Direct participant quotes make insights credible and memorable. 2. **Separate observations from interpretations** — "5 of 8 users clicked the wrong button" is an observation. "The button placement is confusing" is an interpretation. 3. **Quantify where possible** — "Most users" is vague. "7 of 10 users" is specific.
More from anthropics/knowledge-work-plugins
- accessibility-reviewRun a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.
- account-research"Research a company using Common Room data. Triggers on 'research [company]', 'tell me about [domain]', 'pull up signals for [account]', 'what's going on with [company]', or any account-level question."
- analyzeAnswer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
- architectureCreate or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
- audit-supportSupport SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
- brand-reviewReview content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.
- brand-voice-enforcement>
- briefGenerate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
- build-dashboardBuild an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.
- build-zoom-botBuild a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.