customer-interview

customer-interview is a skill for Claude Code from classicchins/compounding-marketing. It costs 49 tokens per session (6,627 once invoked), scanned A, original, MIT.

A guide for planning, conducting, and summarizing customer interviews for product and marketing research.

In plain words
What is it for?
Use it to create interview plans and questions, conduct customer or user calls, and organize findings for product, messaging, and sales work.
Why use it?
It helps interviewers uncover the specific events, concerns, decision criteria, and words behind a customer’s choice instead of collecting only general opinions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the compounding-marketing plugin — 39 skills, 16 commands shipped together

Good fit Use it to create interview plans and questions, conduct customer or user calls, and organize findings for product, messaging, and sales work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/classicchins/compounding-marketing/customer-interview
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add classicchins/compounding-marketing --skill customer-interview
Clone the repo
git clone --depth 1 https://github.com/classicchins/compounding-marketing

Made for: Claude Code.

Or install compounding-marketing, the plugin that ships this one along with the rest of its 39 skills, 16 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for customer-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-interview/github.svg)](https://agentmods.dev/skills/classicchins/compounding-marketing/customer-interview)
Your own site
<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/customer-interview"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-interview/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for customer-interview

Your own site · 80×15
<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/customer-interview"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.06627
Opus 5.5 $0.00020 $0.02651
Sonnet 5.5 $0.00010 $0.01325
Haiku 4.5 $0.00005 $0.00663

Measured 2mo ago against content hash c4811f4e1bd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

customer-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/customer-interview/SKILL.md · 621 lines

How it starts

The opening of the file, as written. The whole thing — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer Interview Guide

You are a senior B2B customer research specialist trained in the JTBD interview tradition (Bob Moesta, Chris Spiek, Indi Young). Your goal is to design and run customer interviews that surface the specific moment of decision in cinematic detail — what triggered the search, what almost stopped the switch, what hiring criteria mattered, what language they actually use — and to turn those interviews into a reliable, codeable evidence base for positioning, messaging, product, and sales work.

A good customer interview is a forensic reconstruction, not a feedback session. You are not asking "do you like the product" — you are asking the customer to walk you back to a specific Tuesday when they realized the spreadsheet was broken and Slacked a peer for a recommendation. The discipline of this skill is to resist the customer's natural urge to rationalize, and to keep pulling them back to the concrete moment. The output is verbatim transcripts coded with switching forces, hiring criteria, anxieties, and the language customers actually use when no marketer is in the room.

This skill covers the full lifecycle: research design, recruitment, scripting, recording, conducting (techniques for listening, probing, and avoiding leading questions), transcription, single-interview synthesis, and cross-interview pattern detection. It is the upstream skill that feeds customer-research, icp-research, positioning, and most messaging work.


Initial Assessment

Before running interviews, get clear on what you're learning and why. Bad research design wastes everyone's time.

Step 0: Prerequisites

  1. Check for product-marketing-context.md — load .agents/product-marketing-context.md. If missing, run the cm-context skill first.
  2. Confirm the decision the research informs — research is expensive (calendar time + customer goodwill). If there's no decision waiting on the output, don't run interviews.
  3. Define the segment — which customers will be interviewed? Don't mix segments in one study (e.g., enterprise + SMB) unless you're explicitly comparing.
  4. Choose interview type — customer (paid, active), lost deal, churned, prospect (never bought), or power user. Each requires a different recruitment pitch and script.

Read the full file on GitHub · 621 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 621 lines · 49 tokens per session scan A c4811f4e1bd1

Subscribe to this mod's changes

customer-interview is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 6,627 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

customer-interview compared with skills from other repositories

customer-interview next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
customer-interviewclassicchins/compounding-marketingSkill85mo agoMITA49Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code