Customer Interview Synthesizer
SkillSkill
Turn 5-30 customer interview transcripts into JTBD-tagged themes, a ranked opportunity map, and a quote bank ready for PRDs and stakeholder reviews.
About
You ran the interviews. Now comes the week of sticky notes.
Customer Interview Synthesizer is an OpenClaw skill that codes every speaker turn in your transcripts with JTBD labels, clusters themes across all your interviews, and renders a frequency-vs-severity opportunity map with sourced quotes — in one pipeline run instead of one exhausting week.
Most research synthesis tools either give you raw transcripts or require a specialized SaaS subscription. This skill runs entirely in your agent, against your files, with no data leaving your machine.
What it does
- Tags every transcript turn with JTBD codes: pain, goal, workaround, anti-goal, job, and quote-worthy
- Clusters codes across 5-30 interviews into named themes with quote counts and source attribution
- Ranks themes by opportunity score (frequency × severity) in a markdown table
- Generates a quote bank per theme with speaker and interview ID — paste directly into a PRD
What's in the package
All files listed below are bundled as fenced code blocks inside SKILL.md — there's no separate folder to install. Copy each code block into its own file using the path shown above it.
- SKILL.md — the full synthesis workflow your agent follows.
- scripts/code_transcript.py — tags a single interview transcript with JTBD codes.
- scripts/cluster_themes.py — clusters codes across all interviews into themes.
- scripts/render_opportunity_map.py — renders the opportunity map table and quote bank as markdown.
- data/jtbd-prompts.md — JTBD code taxonomy with definitions and calibration notes.
- scripts/examples/ — two sample transcripts, coded JSONs, themes.json, and a rendered opportunity map to verify the pipeline works.
How it ships
Drop SKILL.md into ~/.openclaw/skills/customer-interview-synthesizer/. Restart OpenClaw. Run /customer-interview-synthesizer or describe what you need — your agent picks it up.
Pairs well with Linnea (research persona) for full discovery-to-synthesis workflows.
Questions: hackedcubeapps@gmail.com (response within 48 hours).
Core Capabilities
- Code interview transcripts with consistent JTBD/pain/workaround taxonomy
- Cluster themes across 5-30 interviews with quote counts and source attribution
- Rank themes by opportunity score (frequency × severity) in a markdown table
- Generate a quote bank per theme with speaker and interview ID for PRDs and pitches
- Trace every quote back to its source interview for stakeholder credibility
Customer ratings
0 reviews
No ratings yet
- 5 star0
- 4 star0
- 3 star0
- 2 star0
- 1 star0
No reviews yet. Be the first buyer to share feedback.
Version History
This skill is actively maintained.
April 18, 2026
Add TOC; bundled scripts shown inline
April 18, 2026
Initial release with bundled scripts inline
One-time purchase
$19
By continuing, you agree to the Buyer Terms of Service.
Details
- Type
- Skill
- Category
- Research
- Price
- $19
- Version
- 2
- License
- One-time purchase
Works With
Works with OpenClaw, Claude Projects, Custom GPTs. OpenClaw-specific automation may need adaptation.
Works great with
Personas that pair well with this skill.
Linnea — Research Partner
Persona
Linnea is the thinking partner who helps you turn a pile of papers into a point of view — synthesis over summary, every time.
$29
Research Operator
Persona
manually verifying research — get a system that checks it all for you
$29
Dataset Profiler
Bundle
Profile any dataset in minutes — schema, quality, access docs, and analysis potential. Works with CSV, APIs, and open data portals.
$0