Product Discovery Brief Builder
open-mercato/skills
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.
Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework.
Install Mom Test
$ npx skills add getagentseal/founder-playbook --skill mom-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install getagentseal/founder-playbook mom-test --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mom-test .claude/skills/mom-test && rm -rf skills-srcUse ~/.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/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .claude/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-testType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add getagentseal/founder-playbook --skill mom-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install getagentseal/founder-playbook mom-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mom-test .agents/skills/mom-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .agents/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add getagentseal/founder-playbook --skill mom-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install getagentseal/founder-playbook mom-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mom-test .cursor/skills/mom-test && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .cursor/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/getagentseal/founder-playbook.git --path skills/mom-test--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add getagentseal/founder-playbook --skill mom-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install getagentseal/founder-playbook mom-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mom-test .gemini/skills/mom-test && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .gemini/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install getagentseal/founder-playbook mom-testInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add getagentseal/founder-playbook --skill mom-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mom-test .github/skills/mom-test && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .github/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add getagentseal/founder-playbook --skill mom-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install getagentseal/founder-playbook mom-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mom-test .opencode/skills/mom-test && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mom-test" agent skill from https://github.com/getagentseal/founder-playbook/tree/main/skills/mom-test into .opencode/skills/mom-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mom-test", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mom-test- GitHub stars
- 729
- Token cost
- ~2.3k tokens
- SKILL.md length
- 1,167 words
- Files
- 5
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework.
- Works in 3 steps: Talk about their life, not your idea → Ask about specifics in the past, not… → Talk less, listen more
- Planning user interviews
- SKILL.md covers The 3 Core Rules, Decision Tree, Bad Questions (Never Ask) and Good Questions (Use These), plus 16 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Mom Test is an agent skill from getagentseal/founder-playbook. Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework. Use when planning user interviews, getting product feedback, validating ideas, designing discovery questions, or extracting honest signal from biased customer responses. Covers good vs bad questions, deflecting compliments, anchoring fluff, pressing for commitment, and customer slicing.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `cases.md`, `examples.md` and `frameworks.md`).
It sits in Agent Workflows, covering Requirements gathering and User research. The repository describes itself as: 15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor. The licence is MIT.
When your agent uses it
- Planning user interviews
- Getting product feedback
- Validating ideas
- Designing discovery questions
Example prompts
- “Use the mom-test skill to validate business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework”
- “/mom-test”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Talk about their life, not your idea
- Ask about specifics in the past, not generics or opinions about the future
- Talk less, listen more
What it can do on your machine
Read from SKILL.md and the folder at commit e811e63. 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
Mom Test loads about 2.3k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 1,167 words of instructions outside code blocks.
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 getagentseal/founder-playbook at commit e811e63, republished under its MIT licence (© getagentseal). 1,167 words, ~2,284 tokens.
Download SKILL.mdSave it as
.claude/skills/mom-test/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- mom-test
- description
- Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework. Use when planning user interviews, getting product feedback, validating ideas, designing discovery questions, or extracting honest signal from biased customer responses. Covers good vs bad questions, deflecting compliments, anchoring fluff, pressing for commitment, and customer slicing.
Note: This skill is independent analysis and commentary, not a reproduction of the original text. It synthesizes the book's core ideas with modern startup practice, surfaces where frameworks are outdated or incomplete, and integrates perspectives from adjacent disciplines. For the full argument and context, read the original book.
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
The 3 Core Rules
- Talk about their life, not your idea
- Ask about specifics in the past, not generics or opinions about the future
- Talk less, listen more
Decision Tree
Need customer feedback?
├─ Pre-product, no idea what to build → Mom Test (this skill)
├─ Have validated market, packaging product → 100m-offers
├─ Have offer, need traffic → 100m-leads
└─ Selling enterprise → spin-sellingIn a customer conversation?
├─ They're complimenting you → DEFLECT to current behavior
├─ They're speaking in generics ("usually", "always") → ANCHOR to last specific instance
├─ They're requesting features → DIG to underlying motivation
└─ They're committing nothing → PRESS for time/reputation/moneyBad Questions (Never Ask)
| Question | Why It Fails |
|---|---|
| "Do you think it's a good idea?" | Only the market can tell. Opinions are worthless. |
| "Would you buy a product which did X?" | Everyone says yes. Hypotheticals are lies. |
| "How much would you pay for X?" | Numbers feel rigorous but are still lies. |
| "Do you ever..." / "Would you ever..." | Invites fluff and future-tense promises. |
Good Questions (Use These)
| Question | What It Reveals |
|---|---|
| "Why do you bother?" | Real motivation behind perceived problem |
| "What are the implications?" | Must-solve vs nice-to-have |
| "Talk me through the last time that happened." | Concrete past behavior |
| "What else have you tried?" | Whether they care enough to search |
| "How are you dealing with it now?" | Current solution + price anchor |
| "Where does the money come from?" | Budget and purchasing process |
| "Who else should I talk to?" | Tests if they care enough to make intros |
| "Is there anything else I should have asked?" | Catches missed points |
Three Types of Bad Data + Responses
| Bad Data | Example | Response |
|---|---|---|
| Compliments | "That's really cool, I love it." | "Thanks - but how are you dealing with this stuff at the moment?" |
| Fluff | "I usually..." / "I would definitely buy that." | "When's the last time that happened? Walk me through it." |
| Ideas/Features | "Can you add X feature?" | "Why do you want that? What would it let you do? How are you coping without it?" |
Commitment Currencies
Real interest = giving up something valuable. Compliments cost nothing.
| Currency | Examples |
|---|---|
| Time | Clear next meeting, using trial for real, sitting down for feedback |
| Reputation | Intro to peers, intro to boss, public testimonial |
| Money | Letter of intent, pre-order, deposit |
Good Meeting Endings
- "What are the next steps?"
- "When can we start the trial?"
- "Can I buy the prototype?"
- "When can you come back to talk to the rest of the team?"
Polite Rejections (Bad Endings)
- "That's so cool, I love it!"
- "Let me know when it launches."
- "I would definitely buy that."
Critical Principle
They own the problem. You own the solution.
You aren't allowed to tell them what their problem is. They aren't allowed to tell you what to build.
The Filter Test
If they haven't even Googled for a solution, they don't actually care enough to pay for yours.
Customer Slicing
Signs Your Segment Is Too Broad
- 10+ conversations, results all over the map
- Everything "sort of works" but nothing breaks through
- Cannot prove yourself right or wrong
- Every feature is someone's favorite
- Massive price variance ($10 vs $10,000)
The Slicing Process
- Within this group, who would want it MOST?
- Why do they want it? What's their specific problem?
- What are they already doing to solve it?
- Where can we find them?
Good segment test: A segment is useful only if you know WHERE to find them.
Conversation Length Guide
| Duration | Goal |
|---|---|
| 5 min | Does problem exist? Is it important? |
| 10-15 min | Workflow details, what they've tried |
| 1+ hour | Industry deep-dives with experts |
Keep It Casual
- Strip the formality - reduce "meeting" to "chat"
- Pop your most important question immediately
- Goal: they don't even realize they've "had a meeting"
- 5-10 minute casual conversations yield as much as formal meetings
Process Checklist
Before
- Choose focused, findable segment
- Decide 3 big learning goals with team
- Decide ideal next steps and commitments
- Do basic desk research first
During
- Frame the conversation
- Keep it casual
- Ask questions that pass The Mom Test
- Deflect compliments, anchor fluff, dig beneath signals
- Take good notes
- Press for commitment and next steps
After
- Review notes and key quotes with team
- Update beliefs and plans
- Decide next 3 big questions
Show full SKILL.md (470 more words)Show less
Signs You're Doing It Wrong
- You're talking more than they are
- They're complimenting you or your idea
- You don't have notes
- You got an unexpected answer and didn't change anything
- You weren't scared of any question you asked
- You don't know what happens next
- Meeting "went well" but no concrete commitments
Quick Rules
Rules not already captured in the tables and checklists above:
- Customer conversations are bad by default. Your job to fix them.
- People know problems but not solutions. Don't ask what to build.
- You should be terrified of at least one question you're asking (terrified of the answer, not the asking).
- There's more reliable information in a "meh" than a "Wow!"
- It's not a real lead until you've given them a concrete chance to reject you.
Timeline
Spend a week, maybe two. Get your bearings, then give them something to commit to. Don't spend months theorizing.
Context: Founders vs. Product Teams
This framework is written for founders validating whether a new idea is worth pursuing at all. If you're a product manager at an established company, your situation is different: you already know customers want the product. Your interviews are doing problem discovery (what's broken?) or feature discovery (which direction next?) with existing users - not testing whether a market exists. The "press for commitment" and customer-slicing sections are largely irrelevant. The core questioning mechanics (past behavior, avoid hypotheticals, anchor fluff) still apply directly.
When This Doesn't Apply
- Formal B2B/Enterprise: Some contexts require formal protocols
- Regulated industries: Healthcare, finance may need different approaches
- Truly novel innovations: Customers can't imagine what they want until they see it
- Cultural contexts: Japan, Germany, formal corporate cultures expect different protocols
- Domain experts: Expert opinions about THEIR domain carry weight (the rule is about opinions on YOUR IDEA)
Red Flags (Customers to Avoid)
Even enthusiastic, paying customers can derail you:
- Needs so specific they'll pull you off-course
- Demand custom work that doesn't generalize
- "Visionaries" who want something completely different from your vision
- Will only commit if you build their pet feature first
Supporting Files
- frameworks.md - VFWPA email template, ACA framework, deeper question hierarchy, finding-conversations playbook
- cases.md - Earlyvangelist concept (Steve Blank's term, used by Fitzpatrick), case-style examples
- examples.md - Note-taking symbols, full email scripts, conversation walk-throughs
- integration.md - How Mom Test feeds 100m-offers, 100m-leads, spin-selling, obviously-awesome; conflicts with hypothesis-testing approaches
The Nuance
- "Talk less" means don't pitch your solution, not don't talk at all. Strategic questions and redirections are talking.
- "Be terrified of a question" means terrified of the ANSWER (it might invalidate your idea), not asking aggressive questions.
- "Press for commitment" doesn't mean be pushy. Know when to back off. Burning a contact is worse than no commitment.
- "They can't tell you what to build" doesn't mean ignore domain experts. Sophisticated users may know implementation better than you - understand the WHY.
© getagentseal, 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 4 other files in skills/mom-test of getagentseal/founder-playbook.
- SKILL.md
- cases.md
- examples.md
- frameworks.md
- integration.md
Open the folder on GitHubat commit e811e63
Compare with similar skills
Mom Test 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mom Test this skillgetagentseal/founder-playbook | 729 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Product Discovery Brief Builderopen-mercato/skills | 231 | — | ~3k | Automated safety check: Pass | MIT | |
| CE BrainstormEveryInc/compound-engineering-plugin | 25k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Extracting Requirementsprime-radiant-inc/iterative-development | 181 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Foreman Grill DocsVisionForge-OU/foreman | 443 | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Multi-Role Spec and Task Breakdownmylukin/agent-foreman | 250 | — | ~5.1k | Automated safety check: Notes | None |
Similar skills
CE Brainstorm
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
Extracting Requirements
prime-radiant-inc/iterative-development
Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.
Foreman Grill Docs
VisionForge-OU/foreman
Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory.
Multi-Role Spec and Task Breakdown
mylukin/agent-foreman
Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.
Feature Brainstorm
VeryGoodOpenSource/vgv-wingspan
Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.
More from getagentseal/founder-playbook
All 16 skills in this repo100m Leads
getagentseal/founder-playbook
Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100.
100m Offers
getagentseal/founder-playbook
Designs irresistible Grand Slam Offers using Alex Hormozi's value equation, obstacle-solution mapping, value-cost trim/stack, and offer-naming patterns.
Blue Ocean Strategy
getagentseal/founder-playbook
Frameworks from Kim & Mauborgne for creating uncontested market space and making competition irrelevant.
Diagnose
getagentseal/founder-playbook
Startup diagnostic router. An agent skill from getagentseal/founder-playbook.
Influence
getagentseal/founder-playbook
Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion.
Lean Startup
getagentseal/founder-playbook
Applies Eric Ries's Lean Startup methodology for building products under extreme uncertainty.
Related
Questions about Mom Test
What does Mom Test do?
Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework. Mom Test is an agent skill from getagentseal/founder-playbook. Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework.
When should I use Mom Test?
Mom Test fits situations like: planning user interviews; getting product feedback; validating ideas; designing discovery questions.
How do I install Mom Test in Claude Code?
Run `npx skills add getagentseal/founder-playbook --skill mom-test -a claude-code`. Or copy the skill folder (skills/mom-test in getagentseal/founder-playbook) into .claude/skills/mom-test in your project. Claude Code loads it when a task matches its description.
How do I install Mom Test in Codex?
Run `npx skills add getagentseal/founder-playbook --skill mom-test -a codex`. Or copy the skill folder (skills/mom-test in getagentseal/founder-playbook) into .agents/skills/mom-test in your project. Codex loads it when a task matches its description.
Can I use Mom Test 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 getagentseal/founder-playbook --skill mom-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mom-test, .gemini/skills/mom-test, .github/skills/mom-test and .opencode/skills/mom-test in your project.
What does Mom Test need to run?
SKILL.md names no scripts, command-line tools or credentials: Mom Test is instructions for the agent only.
Does Mom Test 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 Mom Test 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 Mom Test use?
Mom Test 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 Mom Test use?
About 2.3k tokens (SKILL.md is roughly 9.1k 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 Mom Test?
Skills that share tags, products or a category with Mom Test: Product Discovery Brief Builder (open-mercato/skills, 231 stars), CE Brainstorm (EveryInc/compound-engineering-plugin, 25k stars), Extracting Requirements (prime-radiant-inc/iterative-development, 181 stars) and Foreman Grill Docs (VisionForge-OU/foreman, 443 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mom Test?
getagentseal (a GitHub organization) maintains it in getagentseal/founder-playbook, which has 729 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.
Source: getagentseal/founder-playbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.