Skip to the usage guide
Affinity Diagramby Owl-Listener

Affinity Diagram Skill.

Turn scattered research observations into themes without letting the first interview dominate the story.

  • UX Research
  • Synthesis
Source Review · Affinity DiagramSKILL.md
Task UX Research Produces • A hierarchy of evidence-backed research themes • Participant-tagged observations supporting each cluster • Prioritized insight statements and single-source flags Before You Start Use an agent that can read the supplied transcripts or notes. Provide participant IDs and the design question; the skill synthesizes existing evidence rather than collecting interviews.
Editorial summary · source reviewed 2026-10-07 · not a generated example

01 What It Does

Affinity Diagram: Find Themes Across Interviews

Bottom-up qualitative clustering with participant-balanced extraction and evidence-backed insight priorities.

Source-based workflowNot an execution benchmark

The Working Approach

Affinity Diagram is for synthesis across multiple qualitative sources. It starts with individual observations, quotes, and notes, then builds natural clusters before naming higher-level themes. It is not a tool for forcing interview evidence into a prewritten category scheme.

The source's strongest distinction is participant coverage. Each transcript is processed fully and each observation tagged before grouping. Every participant should remain represented, while a pattern found in only one interview is marked as single-source rather than discarded or inflated into consensus.

Expected Deliverables

  • A hierarchy of evidence-backed research themes
  • Participant-tagged observations supporting each cluster
  • Prioritized insight statements and single-source flags
See the Example Brief

From Brief to Review

  1. 01
    Extract Across Participants

    Read each supplied source fully and preserve the participant identifier on its observations.

  2. 02
    Cluster Bottom-Up

    Group related observations before selecting theme labels and a higher-level structure.

  3. 03
    Write the Implications

    Explain each theme's design significance, check participant coverage, and distinguish recurring patterns from isolated signals.

02 When to Use It

When to Use It

Use an agent that can read the supplied transcripts or notes. Provide participant IDs and the design question; the skill synthesizes existing evidence rather than collecting interviews.

A Good Fit

  • Multi-Interview SynthesisUse when several sessions or data sources need to be compared.
  • Evidence-Linked DecisionsUseful when a team needs the observation trail behind a proposed design priority.

Limits to Check

  • Not a Single-Transcript SummaryThe source routes that narrower task to an interview-summary skill.
  • Frequency Is Not Population PrevalenceA repeated observation in supplied interviews does not establish how common it is among all users.

Bring These Inputs

  • Raw ResearchSupply transcripts, notes, or responses rather than only a stakeholder summary.
  • Participant IDsUse stable, anonymized identifiers that can survive clustering.
  • Design DecisionExplain which product choices the synthesis should inform.

03 Decisions That Matter

Decisions That Matter

  1. Balanced Coverage

    The explicit participant check resists over-weighting the earliest or most memorable session.

  2. Minority Signals Survive

    Single-source observations remain visible without being represented as shared findings.

04 Try a Focused Brief

Try a Focused Brief

The example brief below has not been tested. Check the skill’s setup before using it.

Review the Setup

Load this task's SKILL.md from the designer-skills repository in your agent's supported skill location. No universal installer command is established by the entry file.

Upstream Source File
https://github.com/Owl-Listener/designer-skills/blob/9a6930cf84a822eb458624bd11c61aac5bbdf224/design-research/skills/affinity-diagram/SKILL.md

Use an agent that can read the supplied transcripts or notes. Provide participant IDs and the design question; the skill synthesizes existing evidence rather than collecting interviews.

Start With One Deliverable

Adapt the scope, source material and constraints in this brief before running the skill.

Example Brief
Use affinity-diagram on these six anonymized interview transcripts. Tag observations by participant, cluster bottom-up, and write evidence-backed insights for our navigation redesign. Show coverage for every participant and flag single-source patterns; do not invent consensus.

Inspect the Result

Check the actual output against these observable criteria.

  • Every supplied participant appears in the synthesis.
  • Themes have traceable observations.
  • Isolated and recurring patterns remain distinguishable.

OpenDesign provides a local design workspace for coding agents. This listing does not mean the skill is bundled or that its external tools, credentials and software dependencies are included.

05 Source and License

Source and License

This page describes the pinned source revision linked below. Upstream behavior and requirements can change.

Source Owner
Owl-Listener
License
MIT
Reviewed Snapshot
2026-10-07 · 9a6930cf84a8
Editorial Source Summary
Bottom-up qualitative clustering with participant-balanced extraction and evidence-backed insight priorities.

Original summary by OpenDesign, based on the linked source. Repository stars are a dated popularity signal, not skill usage or a quality score.

06 Questions Before You Start

Questions Before You Start

Must I provide predefined themes?

No. The source asks for bottom-up grouping before theme names are chosen.

Are unusual observations removed?

No. Single-source patterns should be flagged rather than discarded.

Is this the same as an empathy map?

No. It synthesizes themes across sources; an empathy map focuses on one user or segment's perspective.

OpenDesign

Make Room for the Next Design Iteration.

Keep your brief, source material and design work together in a local workspace. Check the skill’s own setup before adding it to your workflow.

Upstream Source File
https://github.com/Owl-Listener/designer-skills/blob/9a6930cf84a822eb458624bd11c61aac5bbdf224/design-research/skills/affinity-diagram/SKILL.md