affinity-diagram
owl-listener/designer-skills
Cluster qualitative research data into themed insights across multiple interviews and sources.
What is affinity-diagram?
Organize interview notes, observations, and survey responses into natural theme clusters with insight statements. Use this when synthesizing data across multiple sessions or sources; for single transcripts use summarize-interview instead.
- Extract individual observations, quotes, and data points from raw qualitative input
- Group related points into natural bottom-up clusters without predefined categories
- Create descriptive theme labels and organize clusters into 3-5 higher-level themes
- Write insight statements capturing the "so what?" for each theme
- Identify patterns by frequency, intensity, and cross-theme connections
- Rank insights by impact on design decisions
How to install affinity-diagram
npx skills add https://github.com/owl-listener/designer-skills --skill affinity-diagramHow to use affinity-diagram
- 1.Gather all qualitative data sources (interview transcripts, notes, observations, survey responses)
- 2.Provide the data to the skill or reference file paths
- 3.Review the extracted data points to ensure accuracy
- 4.Examine the bottom-up clusters and theme labels generated
- 5.Read insight statements and check participant representation (P1, P2, P3 tags)
- 6.Review pattern rankings by impact on design decisions
- 7.Use the structured hierarchy for design decisions or stakeholder communication
Use cases
- Synthesize findings from 5+ user interviews into actionable design themes
- Consolidate observation data from multiple research sessions into coherent patterns
- Organize survey responses and open-ended feedback into insight clusters
- Identify user needs and pain points across diverse participant groups
- Prepare research synthesis for stakeholder presentations or design sprints
- UX researchers conducting multi-session qualitative studies
- Product managers synthesizing user feedback across sources
- Design teams extracting insights from research data
- User researchers preparing findings for design teams
affinity-diagram FAQ
Use affinity-diagram when synthesizing across multiple interviews or sources. Use summarize-interview for a single transcript, and empathy-map for understanding one participant's inner state.
It tags every observation with participant ID (P1, P2, etc.) before clustering, then verifies each participant appears in the output to prevent over-representing early transcripts.
Single-source patterns are flagged as such rather than discarded, so you can decide whether they represent edge cases or emerging insights worth exploring.
Yes, it works with any qualitative input: interview notes, observation data, survey responses, and mixed formats.
The skill typically organizes data into 3-5 top-level themes with supporting clusters underneath, prioritized by impact on design decisions.
Full instructions (SKILL.md)
Source of truth, from owl-listener/designer-skills.
name: affinity-diagram
description: Cluster many qualitative data points into themes and insight statements. Use when synthesising across multiple sessions or sources. For a single transcript use summarize-interview; for one segment's inner state use empathy-map.
Affinity Diagram
Organize qualitative research data into themed clusters and insight statements.
Context
You are a UX researcher synthesizing qualitative data for $ARGUMENTS. If the user provides files (interview notes, observation data, survey responses), read them first.
Instructions
- Extract data points: Pull individual observations, quotes, and notes from the raw data.
- Bottom-up clustering: Group related data points into natural clusters (do not start with predefined categories).
- Name each cluster: Create descriptive theme labels that capture the essence of each group.
- Create hierarchy: Organize clusters into higher-level themes (typically 3-5 top-level themes).
- Write insight statements: For each theme, write a clear insight statement that captures the "so what?"
- Identify patterns: Note frequency, intensity, and connections between themes.
- Prioritize: Rank insights by impact on design decisions.
- Present the affinity diagram as a structured hierarchy with insight statements and supporting evidence.
Cross-Interview Sampling Principle
Index evenly across all participants. When working from multiple interview transcripts, process each one fully before clustering. Do not over-represent early transcripts or the most recent input.
- Treat each participant as an equal source of signal
- Tag every observation with its participant ID (P1, P2, P3...) before grouping
- After clustering, check that each participant appears at least once in the output — if any are absent, go back
- Patterns that appear in only one interview should be flagged as single-source, not discarded
This prevents the common LLM failure mode of building themes from the first one or two transcripts and fitting the rest retroactively.
Related skills
More from owl-listener/designer-skills and the wider catalog.
animation-principles
Apply animation principles—easing, staging, follow-through—to tune how a single UI motion feels.
card-sort-analysis
Analyze card sort results into proposed groupings and labels for information architecture.
case-study
Craft compelling portfolio case studies with narrative arc, process evidence, and measurable outcomes.
click-test-plan
Design first-click and click tests to measure findability and navigation clarity.
color-system
Build accessible, systematic color palettes with tonal scales, semantic roles, and WCAG contrast compliance.
competitive-analysis
Systematically analyze competitor UX patterns, features, and gaps to inform design strategy.