New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prd V10 Mom Test Interview

by mattgierhart in mattgierhart/PRD-driven-context-engineering

Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption.

MITAuto-check passedProduct & Project Management

Install Prd V10 Mom Test Interview

skills CLI
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v10-mom-test-interview -a claude-code

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

GitHub CLI
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v10-mom-test-interview --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/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v10-mom-test-interview .claude/skills/prd-v10-mom-test-interview && 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
prd-v10-mom-test-interview
GitHub stars
180
Token cost
~2.7k tokens
SKILL.md length
1,213 words
Files
1
Skills in repo
45
Repo updated
First seen
Licence
MIT

At a glance

Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption.

  • Works in 6 steps: Define the goal of this interview → Prep the question list (Mom Test-shaped) → Run the interview → …
  • Requests to interview customers
  • SKILL.md covers Execution Mode, Framework: The Mom Test, Consumes and Produces, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prd V10 Mom Test Interview is an agent skill from mattgierhart/PRD-driven-context-engineering. Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption. Triggers on requests to interview customers, run discovery calls, validate ideas with users, or when user asks "how do I interview customers?", "Mom Test", "Rob Fitzpatrick", "customer interview", "user research without lies", "talking to humans", "discovery conversation". Outputs CFD- discovery entries with Mom Test-calibrated confidence.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering User research, PRD writing and Physical and earth sciences. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.

When your agent uses it

  • Requests to interview customers
  • Run discovery calls
  • Validate ideas with users
  • User asks how do I interview customers?

Example prompts

  • “how do I interview customers?”
  • “Mom Test”
  • “Rob Fitzpatrick”
  • “/prd-v10-mom-test-interview”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Define the goal of this interview
  2. Prep the question list (Mom Test-shaped)
  3. Run the interview
  4. Write up the CFD-* entry within 4 hours
  5. Update the Opportunity Solution Tree [standard+]
  6. Cross-interview synthesis [deep only]

What it can do on your machine

Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep

    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

Prd V10 Mom Test Interview loads about 2.7k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 1,213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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 mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 1,213 words, ~2,722 tokens.

Download SKILL.mdSave it as .claude/skills/prd-v10-mom-test-interview/SKILL.md (or your agent's skills folder).
name
prd-v10-mom-test-interview
description
Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption. Triggers on requests to interview customers, run discovery calls, validate ideas with users, or when user asks "how do I interview customers?", "Mom Test", "Rob Fitzpatrick", "customer interview", "user research without lies", "talking to humans", "discovery conversation". Outputs CFD-* discovery entries with Mom Test-calibrated confidence.
allowed-tools
Read, Write, Edit, Glob, Grep
context
fork
execution_modes.default
standard
execution_modes.supports
quick, standard, deep

Mom Test Interview Discipline

Position in workflow: v1.0 Continuous Discovery (Torres) → v1.0 Mom Test Interview → v1.0 Case Study Builder, Testimonial Collector

Execution Mode

Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.

ModeWhat this skill produces
quickSingle interview prep + question list + CFD-* discovery entry post-interview
standardInterview prep + scripted opening + 5–7 questions + CFD-* entry with confidence calibration + Bad Data flagged
deepMulti-interview cohort plan + cross-interview synthesis + pattern flagging at 3-mention threshold + assumption-test handoff

Framework: The Mom Test

From The Mom Test: How to Talk to Customers and Learn If Your Business is a Good Idea When Everyone is Lying to You (Rob Fitzpatrick, 2013). Premise: People lie to spare your feelings — especially about your business idea. Learn to ask questions that get truth.

The three Mom Test rules
  1. Talk about their life, not your idea. Ask about how they actually live and work, not whether they'd like your hypothetical feature.
  2. Ask about specifics in the past, not generics or opinions about the future. "Last time you faced X, what did you do?" beats "Would you use a tool that does Y?"
  3. Talk less and listen more. If you're talking more than 30% of the time, you're pitching, not learning.
Three types of Bad Data to avoid
Bad Data typeExampleWhy it's badWhat to do
Compliments"That sounds awesome!"Politeness; not predictiveDiscard; don't update confidence
Fluff"I usually..." "I would probably..."Generics, future hypotheticalsAnchor to specifics: "When did you last do that?"
Ideas"You should add X"Solution suggestions disguised as needsNote as IDEA; ask "what would solving X enable you to do?" — get the underlying job
Confidence calibration

Mom Test-disciplined interviews produce higher-confidence CFD- entries because the data is grounded in observed past behavior, not opinion. Confidence floors per P4:

  • 2/5 — Generic statement ("I sometimes have this problem")
  • 3/5 — Specific past instance ("Last Tuesday, I spent 2 hours doing X")
  • 4/5 — Specific past instance + paid-money-for-a-workaround / hired-a-person / built-a-script ("I'm paying $30/mo for a tool that almost solves this")
  • 5/5 — Repeated specific past instances + ongoing willingness to invest in better solution (commit > talk)

Consumes

  • ADO-BEACHHEAD-* and PER-* personas — Defines the interview pool; non-segment interviews are still useful but get lower weight
  • Opportunity Solution Tree (from prd-v10-continuous-discovery-torres) — Interview goals trace to specific opportunities being tested
  • CFD-* prior research — Patterns to validate or contradict
  • KPI-* outcomes — Why we're interviewing (anchor to what we're trying to move)

Produces

  • CFD-* discovery interview entries — One per interview, with confidence calibrated by Mom Test rules
  • CFD-* pattern entries — When 3+ interviews mention the same specific behavior, promote to a pattern entry with frequency
  • Bad Data inventory — Compliments, fluff, ideas captured for context but not data
  • Discovery Tree updates — Each interview either strengthens an opportunity, weakens an opportunity, or surfaces a new one

Execution

Step 1: Define the goal of this interview

Not "validate the idea." Specifically: which opportunity / assumption from the Opportunity Solution Tree is this interview testing?

GoalExample
Validate opportunity exists"Do beachhead pragmatists actually struggle with pricing-tier selection?"
Test assumption"Will users engage with a pricing wizard before signup?"
Map workaround"How are they solving this today?"
Quantify pain"How much time/money does this cost them currently?"

Write the goal at the top of the interview notes.

Step 2: Prep the question list (Mom Test-shaped)

Use specifics-in-the-past form. Avoid hypotheticals.

Bad questionBetter (Mom Test) version
"Would you use a pricing wizard?""Walk me through how you picked the tier when you signed up."
"Do you think analytics is important?""Tell me about the last time you looked at analytics."
"What features do you wish we had?""Tell me about the last time the tool didn't do what you needed."
"How would you describe X?""Tell me about the last time X came up at work."

5–7 questions is plenty for a 25–30 minute interview. Leave room to follow threads.

Step 3: Run the interview
  • Open with a short framing: who you are, why this conversation, no sales pitch
  • Ask the past-behavior questions, listen, follow threads
  • Probe specifics when they generalize: "When was that specifically?" / "What was the dollar / time cost?" / "What did you do next?"
  • Flag Bad Data internally: when they compliment, smile and move on; when they fluff, anchor to specifics; when they suggest ideas, note as IDEA and dig for the underlying job
  • Talk less than 30% of the total minutes
  • Don't pitch. If they ask what you're building, give a one-sentence answer and pivot back
Show full SKILL.md (470 more words)Show less
Step 4: Write up the CFD-* entry within 4 hours

Memory decays fast. Within 4 hours of the interview, write up the CFD- entry. Include:

  • Verbatim quotes (the best evidence)
  • Specific past instances (the gold)
  • Bad Data inventory (compliments, fluff, ideas) — kept for context but not counted as data
  • Confidence per P4 calibration
Step 5: Update the Opportunity Solution Tree [standard+]

Did this interview:

  • Strengthen an existing opportunity (add to frequency count)?
  • Contradict an existing opportunity (note dissenting evidence)?
  • Surface a new opportunity (add to tree)?

Promote a pattern to "Active" focus when 3+ interviews mention the same specific behavior.

Step 6: Cross-interview synthesis [deep only]

After every cohort of 5–8 interviews, synthesize:

  • What patterns emerged at the 3+ mention threshold?
  • What hypotheses were contradicted?
  • What new opportunities surfaced?
  • What's the next interview cohort target?

Output Template

CFD-XXX: Mom Test Interview — [Brief title]
Type: Discovery-Interview
Date: YYYY-MM-DD
Length: [minutes]
Interviewee: [PER-XXX + in-beachhead: yes/no]
Interviewer: [Name]
Goal: [Specific opportunity/assumption being tested]

Specific past instances captured (the gold):
  - "[Verbatim quote — describes a specific past behavior]"
    Context: [When, where, what they did, what it cost]
    Confidence: 3/5 or 4/5 (per P4 calibration)

Workarounds observed:
  - [What they currently do; tools/spend/time invested]

Bad Data (logged but not counted):
  - Compliments: ["That sounds awesome"]
  - Fluff: ["I'd probably use that"]
  - Ideas: ["You should add X"]  → underlying job: [What X would enable]

Pattern strengthening:
  - O1 [opportunity]: +1 mention (now N total)

New opportunity surfaced (if any):
  - [Description]

Overall confidence of this interview's data: X/5
Linked IDs: PER-XXX, ADO-BEACHHEAD-XXX, KPI-XXX, Opportunity-Tree-Node

Anti-Patterns

PatternSignalFix
Pitching disguised as interviewInterviewer talking >40% of the timeTalk less; ask follow-ups; let silence happen
Future-hypothetical questions"Would you use..."Reframe to past-behavior
Treating compliments as data"5 people said it sounds great → strong signal"Compliments are not data; discount
Recording feature requests as opportunities"User asked for dark mode → opportunity: dark mode"Dark mode is a solution; the opportunity is the underlying job (e.g., late-night use, eye strain)
No specifics-probeInterview ends without a single "what specifically" follow-upBuild the habit; specifics are the gold
Writing up days laterInterview Friday, CFD- entry MondayMemory decays; write within 4 hours
No goal for interview"Just talking to users"Each interview tests one specific opportunity or assumption
All interviews from outside beachheadStrong patterns but not in segmentIn-segment interviews dominate; out-of-segment is supplementary

Quality Gates

For each interview:

  • Goal stated before interview (which opportunity/assumption is being tested)
  • Question list is past-behavior shaped, not hypothetical
  • Interviewer talked <30% of minutes
  • At least one "what specifically" follow-up was asked
  • Bad Data inventory exists (compliments / fluff / ideas — even if empty)
  • CFD- entry written within 4 hours
  • Confidence per P4 calibration (not "feels good")
  • Discovery Tree updated (pattern strengthen / contradict / new opportunity)

Downstream Connections

ConsumerWhat it usesExample
Continuous Discovery (Torres)Every interview updates the Opportunity Solution TreeThis skill is the how; Torres is the what to do with
Chasm Adoption (Moore)In-beachhead interviews update ADO-STAGE-* and ADO-BEACHHEAD-*Patterns strengthen stage assessment
Case Study BuilderHigh-impact interviewees become case-study candidatesCFD- with 5/5 confidence + outcome → ADO-REF-*
Testimonial CollectorStrong endorsement interviews become testimonial sourcesSpecific past-instance quote + consent → testimonial
Feedback Loop SetupMom Test is the discipline for the structured-interview armInbound feedback ≠ Mom Test (still useful, lower confidence)

Detailed References

  • Rob Fitzpatrick, The Mom Test (2013) — canonical source, short and readable
  • Rob Fitzpatrick, The Workshop Survival Guide (companion)
  • Steve Portigal, Interviewing Users (complementary depth)
  • wondelai's mom-test skill (wondelai/skills)
  • (No bundled references/ — read the book; it's 130 pages)

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

Files

Just SKILL.md in .claude/skills/prd-v10-mom-test-interview of mattgierhart/PRD-driven-context-engineering.

Open the folder on GitHubat commit 30ed1b0

Compare with similar skills

Prd V10 Mom Test Interview 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.

Prd V10 Mom Test Interview compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd V10 Mom Test Interview this skillmattgierhart/PRD-driven-context-engineering180—~2.7kAutomated safety check: PassMIT
Produck Feedback To Buildtryproduck/produck-skills511—~1kAutomated safety check: PassApache-2.0
Discovery Synthesisandreaskelm/pm-brain234—~2.3kAutomated safety check: PassCustom licence
Product Manager Toolkitdavila7/claude-code-templates33k7 repos~2.2kAutomated safety check: PassMIT
User ResearchTechNomadCode/AI-Product-Development-Toolkit1k—~266Automated safety check: PassMIT
Customer Interviewsmenkesu/awesome-pm-skills434—~4.4kAutomated safety check: PassCustom licence

Similar skills

  • 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.

    511 GitHub stars~1k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

  • Discovery Synthesis

    andreaskelm/pm-brain

    Plan customer discovery, turn interview snapshots into synthesis and evidence-based opportunities, build or update an Opportunity Solution Tree, map jobs and segments, and design RAT tests for the…

    234 GitHub stars~2.3k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Product Manager Toolkit

    davila7/claude-code-templates

    Scores feature requests with RICE, mines customer interview transcripts for pain points, and offers PRD templates, with two Python scripts behind it.

    33k GitHub starsUsed in 7 repos~2.2k tokens
    Product & Project ManagementAuto-check passed

  • User Research

    TechNomadCode/AI-Product-Development-Toolkit

    Plan a user research questionnaire, or turn collected responses into evidence-linked input for a PRD, with the AI Product Development Toolkit's research prompts.

    1k GitHub stars~266 tokensUpdated 5 days ago
    Product & Project ManagementAuto-check passed

  • Customer Interviews

    menkesu/awesome-pm-skills

    Designs customer interviews and turns the transcripts into decisions.

    434 GitHub stars~4.4k tokensUpdated 4 days ago
    Product & Project ManagementAuto-check passed

  • Product Management

    julianromli/opencode-template

    Assist with core product management activities including writing PRDs, analyzing features, synthesizing user research, planning roadmaps, and communicating product decisions.

    144 GitHub starsUsed in 1 repo~3.4k tokens
    Product & Project ManagementAuto-check passed

More from mattgierhart/PRD-driven-context-engineering

All 45 skills in this repo

  • Ghm Gate Check

    mattgierhart/PRD-driven-context-engineering

    Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).

    180 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check: notes

  • Ghm Harvest

    mattgierhart/PRD-driven-context-engineering

    Extracts durable insights from temp/ files to SoT during EPIC Phase E.

    180 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Ghm Id Register

    mattgierhart/PRD-driven-context-engineering

    Validates and registers new SoT IDs with cross-reference integrity.

    180 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Ghm Sot Builder

    mattgierhart/PRD-driven-context-engineering

    Creates new Source of Truth (SoT) files when existing templates don't fit your needs.

    180 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Prd V01 Problem Framing

    mattgierhart/PRD-driven-context-engineering

    Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.

    180 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Prd V01 User Value Articulation

    mattgierhart/PRD-driven-context-engineering

    Transform validated pain points into articulated user value statements for PRD v0.1 Spark.

    180 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Prd V10 Mom Test Interview

What does Prd V10 Mom Test Interview do?

Apply Rob Fitzpatrick's Mom Test discipline to customer interviews during PRD v1.0 Market Adoption. Prd V10 Mom Test Interview is an agent skill from mattgierhart/PRD-driven-context-engineering.0 Market Adoption.

When should I use Prd V10 Mom Test Interview?

Prd V10 Mom Test Interview fits situations like: requests to interview customers; run discovery calls; validate ideas with users; user asks how do I interview customers?.

How do I install Prd V10 Mom Test Interview in Claude Code?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v10-mom-test-interview -a claude-code`. Or copy the skill folder (.claude/skills/prd-v10-mom-test-interview in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v10-mom-test-interview in your project. Claude Code loads it when a task matches its description.

How do I install Prd V10 Mom Test Interview in Codex?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v10-mom-test-interview -a codex`. Or copy the skill folder (.claude/skills/prd-v10-mom-test-interview in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v10-mom-test-interview in your project. Codex loads it when a task matches its description.

Can I use Prd V10 Mom Test Interview 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 mattgierhart/PRD-driven-context-engineering --skill prd-v10-mom-test-interview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v10-mom-test-interview, .gemini/skills/prd-v10-mom-test-interview, .github/skills/prd-v10-mom-test-interview and .opencode/skills/prd-v10-mom-test-interview in your project.

What does Prd V10 Mom Test Interview need to run?

SKILL.md names no scripts, command-line tools or credentials: Prd V10 Mom Test Interview is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep.

Does Prd V10 Mom Test Interview 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 Prd V10 Mom Test Interview 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 Prd V10 Mom Test Interview use?

Prd V10 Mom Test Interview 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 Prd V10 Mom Test Interview use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prd V10 Mom Test Interview?

Skills that share tags, products or a category with Prd V10 Mom Test Interview: Produck Feedback To Build (tryproduck/produck-skills, 511 stars), Discovery Synthesis (andreaskelm/pm-brain, 234 stars), Product Manager Toolkit (davila7/claude-code-templates, 33k stars) and User Research (TechNomadCode/AI-Product-Development-Toolkit, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd V10 Mom Test Interview?

mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.

Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.