Agent skill

Customer Interviews

by RefoundAI in RefoundAI/lenny-skills

Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

MITAuto-check passedProduct & Project Management

Install Customer Interviews

skills CLI
$ npx skills add RefoundAI/lenny-skills --skill customer-interviews -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RefoundAI/lenny-skills customer-interviews --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/customer-interviews .claude/skills/customer-interviews && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
customer-interviews
GitHub stars
1.4k
Token cost
~1.7k tokens
SKILL.md length
970 words
Files
3 (incl. references)
Skills in repo
76
Repo updated
First seen
Licence
MIT

At a glance

Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

  • Works in 4 steps: Define objectives - Identify the… → Draft the guide - Create open-ended… → Synthesize findings - Analyze interview… → …
  • Tasks that involve User research
  • SKILL.md covers How to Help, Core Principles, Templates & Frameworks and Questions to Help Users, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Customer Interviews is an agent skill from RefoundAI/lenny-skills. Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/artifacts.md` and `references/guest-insights.md`).

It sits in Product & Project Management, covering User research. The repository describes itself as: 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more. The licence is MIT.

When your agent uses it

  • Tasks that involve User research

Example prompts

  • “/customer-interviews”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Define objectives - Identify the specific problem area or user segment you want to explore before recruiting participants.
  2. Draft the guide - Create open-ended questions that focus on past behaviors and struggling moments rather than hypothetical opinions.
  3. Synthesize findings - Analyze interview notes to distinguish between polite encouragement and genuine user pull.
  4. Validate pain - Evaluate whether the identified problems are painful enough to warrant a new solution or behavioral change.

What it can do on your machine

Read from SKILL.md and the folder at commit 13598cc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Customer Interviews loads about 1.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 970 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RefoundAI/lenny-skills at commit 13598cc, republished under its MIT licence (© RefoundAI). 970 words, ~1,695 tokens.

Download SKILL.mdSave it as .claude/skills/customer-interviews/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
customer-interviews
description
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

Mastering Customer Interviews

Uncover deep user pain and behavioral triggers to build products people actually need.

Help the user with mastering customer interviews using insights from 11 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Define objectives - Identify the specific problem area or user segment you want to explore before recruiting participants.
  2. Draft the guide - Create open-ended questions that focus on past behaviors and struggling moments rather than hypothetical opinions.
  3. Synthesize findings - Analyze interview notes to distinguish between polite encouragement and genuine user pull.
  4. Validate pain - Evaluate whether the identified problems are painful enough to warrant a new solution or behavioral change.

Core Principles

Focus on causal triggers

Bob Moesta: "And so the real heart of the method of Jobs to Be Done is understanding the causation of what pushes people to say, 'Today's the day I got to do something different.'"

Interviews should uncover the specific events and context that led to a change in behavior. Understanding the struggling moment makes seemingly irrational user choices appear rational.

Observe unarticulated pain

Jag Duggal: "You make sure that you focus on customer discovery before you start building. You make sure that that discovery is focused not simply on asking the customer, but on innovating on their behalf."

Effective research goes beyond listening to explicit requests by observing users in their natural environment. This reveals friction points that users may not be able to describe.

Actively seek disproof

Shaun Clowes: "Avoid availability or confirmation bias. Most of the time people go talk to the people they always talk to and they learn nothing particularly new. They don't synthesize the results that they got from that conversation. They don't seek out the counterfactual, they don't seek out the proof that they're wrong."

To avoid confirmation bias, you must intentionally seek out data points that disprove your current assumptions. Learning is maximized when you find counterfactual perspectives.

Prioritize direct observation

From "How to develop product sense": "Don’t just read reports from researchers on your team; instead attend user research sessions to get firsthand exposure to user experiences and reactions. What’s important is to pay attention to micro details and ask yourself why people react to your product the way they do."

Directly observing user behavior provides a firsthand understanding of emotional and functional needs. Research reports often overlook the nuance found in live reactions.

Avoid the sales pitch

From "Startup to exit: Lessons from a first-time founder": "However, we realized our first several “interviews” were actually sales pitches (e.g. “here’s this cool new thing, what do you think?”). Far too biased to get any real signal."

Running discovery calls as sales pitches prevents honest signals. Use an unbiased script that avoids mentioning your specific solution to see if the customer brings up the problem organically.

Listen for signs of pull

From "What to do if your product isn’t taking off": "When talking to people, look for two things: pain and pull. Pain tells you there’s an opportunity to solve a problem. Pull tells you that you’re actually solving the problem."

Ignore polite encouragement and look for signs of intense pain. Real pull is evidenced by people paying money or continuing to use a bad prototype despite its flaws.

Show full SKILL.md (429 more words)Show less

Templates & Frameworks

  • Jobs-to-be-Done Interrogation Technique (Robby Stein) - Clayton Christensen's interview/interrogation method for understanding why users hire a product, distinguishing utility jobs from emotional jobs
  • Nielsen Number for Research Right-Sizing (Shaun Clowes) - The principle that 7-14 user interviews is the sweet spot—fewer than 7 means not enough data, more than 14 means diminishing returns.
  • Four Signals of Pain and Pull (What to do if your product isn’t taking off) - Four concrete indicators that tell you whether your product is solving a real problem, used during customer discovery conversations
  • Gusto's Emotional Reaction Test for Customer Interviews (How to validate your B2B startup idea) - A framework for evaluating whether customer interview feedback indicates genuine demand, based on the intensity of emotional response
  • Story-Based Interview Technique (Teresa Torres) - An interviewing method where you collect specific behavioral stories from customers by asking about a recent concrete experience and then following the timeline
  • Automated Customer Interview Recruiting System (Teresa Torres) - A system for automating weekly customer interview scheduling so product teams can maintain a continuous interviewing cadence without manual recruiting effort
  • Seven Signals to Look for in User Conversations (Prioritizing at startups) - What to listen for when talking to early users and potential users to generate product ideas

See references/artifacts.md for the full list with details.

Questions to Help Users

  • "What specific event or struggling moment led you to look for a solution to this problem?"
  • "Can you walk me through the last time you dealt with this, step by step?"
  • "How are you currently solving this, and what specifically annoys you about that approach?"
  • "If you had a magic wand and could change anything about your current workflow, what would it be?"
  • "What would happen if you did nothing and just continued with the way things are today?"
  • "Are there any tools or workarounds you have tried in the past that didn't work out?"

Common Mistakes to Flag

  • Leading the witness - Asking if a customer likes an idea invites polite validation rather than honest behavioral data.
  • Stopping at feature requests - Accepting a list of features without understanding the underlying 'job' leads to bloated products that don't solve the root problem.
  • Interviewing too many or too few people - Fewer than seven interviews provides insufficient data, while more than fourteen often leads to diminishing returns in new insights.
  • Mistaking interest for intent - Users often say an idea is 'cool' to be nice, but only 'pull' signals like spending money or time indicate real demand.

Deep Dive

For all 14 sourced insights from 11 guests, see references/guest-insights.md

  • Continuous Discovery
  • Idea Validation
  • Product Experiments
  • Defining Icp

© RefoundAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/customer-interviews of RefoundAI/lenny-skills.

  • SKILL.md
  • references/artifacts.md
  • references/guest-insights.md

Open the folder on GitHubat commit 13598cc

Compare with similar skills

Customer Interviews next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Customer Interviews compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Customer Interviews this skillRefoundAI/lenny-skills1.4k—~1.7kAutomated safety check: PassMIT
User Research Cookiycookiy-ai/user-research-skill1.6k—~954Automated safety check: PassMIT
Fable DomainSahir619/fable-method2.3k—~2.6kAutomated safety check: PassMIT
Produck Feedback To Buildtryproduck/produck-skills510—~1kAutomated safety check: PassApache-2.0
MITRE Problem Framing Canvasdeanpeters/Product-Manager-Skills7.2k2 repos~4.5kAutomated safety check: PassCustom licence
Product Discovery Brief Builderopen-mercato/skills227—~3kAutomated safety check: PassMIT

Similar skills

  • User Research Cookiy

    cookiy-ai/user-research-skill

    End-to-end user research assistant — qualitative and quantitative.

    1.6k GitHub stars~954 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Fable Domain

    Sahir619/fable-method

    Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…

    2.3k GitHub stars~2.6k tokensUpdated 5 days ago
    Product & Project ManagementAuto-check passed
  • Produck Feedback To Build

    tryproduck/produck-skills

    Pulls full in-context user feedback tickets through the Produck MCP server and turns them into an aligned product change instead of a guess.

    510 GitHub stars~1k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • MITRE Problem Framing Canvas

    deanpeters/Product-Manager-Skills

    Guides a three-phase canvas, looking inward, looking outward, then reframing, to produce an equity-aware problem statement.

    7.2k GitHub starsUsed in 2 repos~4.5k tokens
    Product & Project ManagementAuto-check passed
  • Guides a product discovery conversation and writes product-brief.md with the problem, evidence, scope, decisions and the next open question, for existing, client or own ideas.

    227 GitHub stars~3k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Ingest User Interview

    egregore-labs/egregore

    Analyze a user interview from Granola, pasted text, or a file into an evidence-backed briefing, journey insights, product findings, patterns, and actions.

    291 GitHub stars~689 tokensUpdated 6 days ago
    Product & Project ManagementAuto-check passed

More from RefoundAI/lenny-skills

All 76 skills in this repo
  • Time Energy Management

    RefoundAI/lenny-skills

    Help users master their personal output by shifting from reactive scheduling to intentional energy management, internal trigger mastery, and proactive boundary setting.

    1.4k GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • User Onboarding Activation

    RefoundAI/lenny-skills

    Help users reach their first moment of core value by optimizing the first-run experience, removing friction, and aligning product design with psychological triggers.

    1.4k GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Acquisition Channels

    RefoundAI/lenny-skills

    Help users identify unique distribution advantages and master the lifecycle of acquisition channels to build a sustainable engine for growth and retention.

    1.4k GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • AI Assisted Prototyping

    RefoundAI/lenny-skills

    Help users build functional product prototypes from natural language or visual mocks using AI coding tools.

    1.4k GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • AI Evals

    RefoundAI/lenny-skills

    Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.

    1.4k GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • AI Native UX

    RefoundAI/lenny-skills

    Help users interact with probabilistic models by designing interfaces that manage fluidity, intent, and agency while maintaining trust and control.

    1.4k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Customer Interviews

What does Customer Interviews do?

Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers. Customer Interviews is an agent skill from RefoundAI/lenny-skills. Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

When should I use Customer Interviews?

Customer Interviews fits situations like: tasks that involve User research.

How do I install Customer Interviews in Claude Code?

Run `npx skills add RefoundAI/lenny-skills --skill customer-interviews -a claude-code`. Or copy the skill folder (skills/customer-interviews in RefoundAI/lenny-skills) into .claude/skills/customer-interviews in your project. Claude Code loads it when a task matches its description.

How do I install Customer Interviews in Codex?

Run `npx skills add RefoundAI/lenny-skills --skill customer-interviews -a codex`. Or copy the skill folder (skills/customer-interviews in RefoundAI/lenny-skills) into .agents/skills/customer-interviews in your project. Codex loads it when a task matches its description.

Can I use Customer Interviews in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RefoundAI/lenny-skills --skill customer-interviews -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/customer-interviews, .gemini/skills/customer-interviews, .github/skills/customer-interviews and .opencode/skills/customer-interviews in your project.

What does Customer Interviews need to run?

SKILL.md names no scripts, command-line tools or credentials: Customer Interviews is instructions for the agent only.

Does Customer Interviews access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Customer Interviews safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Customer Interviews use?

Customer Interviews is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Customer Interviews use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.7k tokens, read only when the agent opens those files.

What are the alternatives to Customer Interviews?

Skills that share tags, products or a category with Customer Interviews: User Research Cookiy (cookiy-ai/user-research-skill, 1.6k stars), Fable Domain (Sahir619/fable-method, 2.3k stars), Produck Feedback To Build (tryproduck/produck-skills, 510 stars) and MITRE Problem Framing Canvas (deanpeters/Product-Manager-Skills, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Customer Interviews?

RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,377 GitHub stars. The repository holds 76 skills in this directory. The repository was last updated on July 16, 2026.

Source: RefoundAI/lenny-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.