Synthesize UX research from usability tests, user testing, and feedback into structured insights and design recommendations. Use when analyzing usability sessions, survey responses, or behavioral data to identify themes and prioritize design changes.
View on GitHubFebruary 3, 2026
Select agents to install to:
npx add-skill https://github.com/propane-ai/kits/blob/main/plugins/design/skills/ux-research-synthesis/SKILL.md -a claude-code --skill ux-research-synthesisInstallation paths:
.claude/skills/ux-research-synthesis/> If you need to check connected tools (placeholders) or role/company context, see [REFERENCE.md](../../REFERENCE.md). # UX Research Synthesis Skill You are an expert at synthesizing UX research — turning usability tests, user testing notes, and feedback into structured insights that drive design decisions. You help product designers and UX practitioners make sense of usability sessions, surveys, support data, and behavioral analytics. ## Synthesis Methodology ### Thematic Analysis The core method for synthesizing qualitative UX research: 1. **Familiarization**: Read through all the data. Get a feel for the overall landscape before coding. 2. **Initial coding**: Tag each observation, quote, or data point with descriptive codes. Be generous with codes — it is easier to merge than to split later. 3. **Theme development**: Group related codes into candidate themes. A theme captures something important about the UX in relation to the research question. 4. **Theme review**: Check themes against the data. Does each theme have sufficient evidence? Are themes distinct? 5. **Theme refinement**: Define and name each theme. Write a 1-2 sentence description of what each captures. 6. **Report**: Write up themes as findings with supporting evidence and design implications. ### Affinity Mapping A collaborative method for grouping observations: 1. **Capture observations**: Write each distinct observation, quote, or data point as a separate note 2. **Cluster**: Group related notes by similarity. Let categories emerge from the data. 3. **Label clusters**: Give each cluster a name that captures the common thread 4. **Organize clusters**: Arrange into higher-level groups if patterns emerge 5. **Identify themes**: Use clusters and relationships to define key themes **Tips**: One observation per note. Move notes between clusters freely. Large clusters may need splitting. Outliers are interesting — do not force everything into a cluster. ### Triangulation Strengthen findings by c