Affinity Diagram
Turn interview notes, observations, and survey qual into bottom-up theme clusters and prioritized insight statements for product decisions.
Overview
Affinity Diagram is an agent skill for the Idea phase that organizes qualitative research into themed clusters and prioritized insight statements from interviews, observations, or surveys.
Install
npx skills add https://github.com/owl-listener/designer-skills --skill affinity-diagramWhat is this skill?
- Eight-step flow: extract points → bottom-up clusters → name themes → hierarchy → insight statements → patterns → priorit
- Bottom-up clustering without predefined categories to avoid confirmation bias
- 3–5 top-level themes with supporting quotes and evidence per insight
- Prioritization ranked by impact on design decisions
- Reads user-supplied interview notes, observation data, or survey files when provided
- 8-step synthesis instructions
- 3–5 top-level themes typical in hierarchy
Adoption & trust: 564 installs on skills.sh; 1.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have stacks of interview and survey qual but no shared structure, so themes feel anecdotal and design priorities stay argumentative.
Who is it for?
Solo founders or designers synthesizing 5–50+ qualitative data points after user interviews or field observations.
Skip if: Purely quantitative analytics dashboards or A/B readouts where cluster-by-quote synthesis is not the input.
When should I use this skill?
Synthesizing large amounts of qualitative data from interviews, observations, or surveys into an affinity diagram with themes, clusters, and insight statements.
What do I get? / Deliverables
You deliver a hierarchical affinity diagram with named themes, insight statements, evidence, and a priority rank ready for scope and prototype decisions.
- Structured affinity hierarchy with theme labels
- Insight statements with supporting evidence per theme
- Prioritized insight list for design decisions
Recommended Skills
Journey fit
Idea/research is where qualitative discovery happens before scope lock; affinity synthesis is the standard ritual after fieldwork. Research subphase covers synthesizing user interviews, observations, and open-ended survey responses into actionable themes.
How it compares
Use for bottom-up qual synthesis instead of jumping straight to personas or feature lists without evidence clustering.
Common Questions / FAQ
Who is affinity-diagram for?
Builders and UX-minded solo operators who collect qualitative research and need defensible themes before committing to features or copy.
When should I use affinity-diagram?
In the Idea research phase after interviews, observations, or open-ended surveys—especially when synthesizing large amounts of qualitative data.
Is affinity-diagram safe to install?
The skill processes research content you provide; check the Security Audits panel on this Prism page and avoid pasting secrets into notes files.
SKILL.md
READMESKILL.md - Affinity Diagram
# 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 1. **Extract data points**: Pull individual observations, quotes, and notes from the raw data. 2. **Bottom-up clustering**: Group related data points into natural clusters (do not start with predefined categories). 3. **Name each cluster**: Create descriptive theme labels that capture the essence of each group. 4. **Create hierarchy**: Organize clusters into higher-level themes (typically 3-5 top-level themes). 5. **Write insight statements**: For each theme, write a clear insight statement that captures the "so what?" 6. **Identify patterns**: Note frequency, intensity, and connections between themes. 7. **Prioritize**: Rank insights by impact on design decisions. 8. Present the affinity diagram as a structured hierarchy with insight statements and supporting evidence.