summarize-interview · owl-listener — Claude Code skill: what it does, how to install
Turns a single interview transcript into themes, quotes and follow-up tasks, in a format you can hand to stakeholders.
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a claude-codeWhat summarize-interview does
The skill reads one transcript and fills in a fixed set of sections: who the participant was, the main themes with quotes attached, the jobs they were trying to get done, pain points graded by severity, workarounds, what delighted them, quotes worth keeping, surprises and follow-up tasks.
It also tags every insight as either stated by the participant or inferred by the model. That line matters when you reopen the summary weeks later and need to know which parts came straight from the transcript.
Feed it a transcript file or paste the text in; there is nothing to analyse without one. It handles a single session. Synthesising several interviews at once is the job of affinity-diagram from the same collection.
What it helps with
- sort a long transcript into themes with supporting quotes
- pull quotes you can paste into a report
- mark which findings were stated outright and which you inferred
- log pain points with a severity rating
- get follow-up tasks while the session is still fresh
Example prompts for the agent
- Summarize
interview-07.mdinto themes, quotes, pain points and action items. - Go through this transcript and note for each finding whether the participant said it or you inferred it.
- What surprised us in this interview, compared with our assumptions?
How to install summarize-interview
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a claude-code2Manually: put the files in place
~/.claude/skills/summarize-interview/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/summarize-interview/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a codex2Manually: put the files in place
.agents/skills/summarize-interview/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a cursor2Manually: put the files in place
.cursor/skills/summarize-interview/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Owl-Listener/designer-skills summarize-interview2Manually: put the files in place
.github/skills/summarize-interview/SKILL.md1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a gemini-cli2Platform CLI
gemini skills install https://github.com/Owl-Listener/designer-skills --path design-research/skills/summarize-interviewManually: put the files in place
.devin/skills/summarize-interview/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill summarize-interview -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about summarize-interview
How do I install summarize-interview in Claude Code?
Run npx skills add Owl-Listener/designer-skills --skill summarize-interview -a claude-code. The skill lands at ~/.claude/skills/summarize-interview/SKILL.md.
What does summarize-interview do?
It reads one interview transcript and builds a structured summary: themes, quotes, jobs-to-be-done, pain points, workarounds and action items. Each insight is flagged as stated or inferred.
How is it different from affinity-diagram?
This one covers a single session. To combine several interviews, the same collection has affinity-diagram.
Source text
SKILL.md · MIT
--- name: summarize-interview description: Turn one interview transcript into themes, supporting quotes, and action items. Use immediately after a session. For synthesising many sessions at once, use `affinity-diagram`. --- # Summarize Interview Summarize a user interview transcript into structured, actionable insights. ## Context You are a senior UX researcher summarizing an interview transcript for $ARGUMENTS. The user will provide a transcript file or paste the transcript text. ## Instructions 1. **Read the transcript** carefully, noting key moments. 2. **Create a structured summary** with: - **Participant profile**: Role, context, experience level - **Key themes**: 3-5 major themes that emerged, with supporting quotes - **Jobs-to-be-done**: What the participant is trying to accomplish - **Pain points**: Frustrations, barriers, and unmet needs (with severity) - **Workarounds**: How they currently solve problems - **Delighters**: What works well or exceeds expectations - **Notable quotes**: 5-8 verbatim quotes that capture key insights - **Surprises**: Anything unexpected or counter to assumptions - **Action items**: Specific design or research follow-ups suggested by the findings 3. **Rate confidence**: For each insight, note whether it was explicitly stated or inferred. 4. Present in a clear, scannable format suitable for sharing with stakeholders.
© Owl-Listener · MIT · Owl-Listener/designer-skills
Similar skills
Everything for Design →summarize-interview by other authors comes first.