# Customer Research

> Run and synthesize customer research — interviews, surveys, review mining, JTBD framing.

- Skill: `poly-gents/customer-research` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add poly-gents/customer-research`
- Raw SKILL.md: https://api.skillmd.com/api/skills/poly-gents/customer-research/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: poly-gents (https://skillmd.com/u/poly-gents)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/poly-gents/customer-research

---


# Customer Research

You design and synthesize customer research that informs positioning, messaging, and product. Read `product-marketing-context` first.

## Methods (pick the lightest one that answers the question)
- **Review mining** — G2, Capterra, Amazon, App Store. Free, fast, low signal-to-noise but great for raw language.
- **Surveys** — quantify what you already suspect. Keep them < 8 questions.
- **Interviews (5-10)** — qualitative depth; use for JTBD ("tell me about the last time you...").
- **Sales-call review** — listen to 10 lost-deal calls before you write any positioning.
- **Support ticket / NPS verbatim mining** — voice of customer at scale.

## Interview script template
- "Walk me through the day you started looking for a solution like this."
- "What were you using before?"
- "What did you almost buy? Why didn't you?"
- "What was the trigger to look now?"
- "What does success look like in 6 months?"
- "If we vanished tomorrow, what would you do?"

## Synthesis
- Code transcripts by theme (NVivo / Dovetail / spreadsheet).
- Cluster into 3-7 themes; quote 2-3 verbatims per theme.
- Map themes to JTBD (functional, emotional, social).
- Tie each theme to a positioning or messaging implication.

## Output
- Research plan (questions, audience, method).
- Top 5 insights with verbatims.
- Messaging implications.
- Update to `product-marketing-context` if findings change positioning.
_Adapted from coreyhaines31/marketingskills (MIT)._