Agent skill

Mom Test

by wondelai in wondelai/skills

Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less.

MITAuto-check passedProduct & Project Management

Install Mom Test

skills CLI
$ npx skills add wondelai/skills --skill mom-test -a claude-code

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

GitHub CLI
$ gh skill install wondelai/skills mom-test --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/wondelai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mom-test .claude/skills/mom-test && 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
mom-test
GitHub stars
2.4k
Token cost
~4.2k tokens
SKILL.md length
2,265 words
Files
7 (incl. references)
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less.

  • Works in 6 steps: The Mom Test Rules → Good vs Bad Questions → Avoiding Compliments and Opinions → …
  • The user mentions customer interviews
  • SKILL.md covers Core Principle, Scoring, Framework Sections and Common Mistakes, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mom Test is an agent skill from wondelai/skills. Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less. Use when the user mentions "customer interviews", "validate my idea", "users say they want it but dont buy", "leading questions", "The Mom Test", "customer feedback bias", or "interview script". Also trigger when preparing user-research questions, interpreting ambiguous feedback, or designing customer-discovery that avoids false positives. Covers commitment and…

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/avoiding-bad-data.md`, `references/case-studies.md` and `references/commitment-advancement.md`).

It sits in Product & Project Management, covering User research, Product strategy and Customer feedback analysis. The repository describes itself as: Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io… The licence is MIT.

When your agent uses it

  • The user mentions customer interviews
  • Validate my idea
  • Users say they want it but dont buy
  • Leading questions

Example prompts

  • “customer interviews”
  • “validate my idea”
  • “users say they want it but dont buy”
  • “/mom-test”

Workflow steps

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

  1. The Mom Test Rules
  2. Good vs Bad Questions
  3. Avoiding Compliments and Opinions
  4. Commitment and Advancement
  5. Finding Conversations
  6. Processing and Learning

What it can do on your machine

Read from SKILL.md and the folder at commit c172996. 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

    Links to these hosts (documentation or services it may open):

    • amazon.com

    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 4.2k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 169 tokens; SKILL.md has 2,265 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~169
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~23k

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 wondelai/skills at commit c172996, republished under its MIT licence (© wondelai). 2,265 words, ~4,205 tokens.

Download SKILL.mdSave it as .claude/skills/mom-test/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
mom-test
description
Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less. Use when the user mentions "customer interviews", "validate my idea", "users say they want it but dont buy", "leading questions", "The Mom Test", "customer feedback bias", or "interview script". Also trigger when preparing user-research questions, interpreting ambiguous feedback, or designing customer-discovery that avoids false positives. Covers commitment and advancement, avoiding compliments, and extracting signal from noise. For product-market fit, see jobs-to-be-done. For rapid prototype testing, see design-sprint.
license
MIT
metadata.author
wondelai
metadata.version
1.4.0

The Mom Test Framework

Framework for customer conversations that won't lead you astray, based on a fundamental truth: everyone is lying to you -- not maliciously, but because you're asking the wrong questions. The Mom Test provides rules for asking questions so good that even your mom can't lie to you.

Core Principle

Good customer conversations are about their life, not your idea. The moment you mention what you're building, people switch from sharing truth to performing politeness. Talk about their problems, their lives, and their existing behavior instead of pitching, and ask about specifics in the past, not hypotheticals about the future. Above all, talk less and listen more.

Scoring

Goal: 7/7. Score a conversation (or interview plan) by the seven-row Quick Diagnostic below: 1 point per row that passes.

  • 6-7 = focused on their life and past behavior, concrete facts captured, a real commitment (time/reputation/money) secured, they talked 80%+, and beliefs got updated.
  • 4-5 = some past-behavior facts but leaking into hypotheticals, compliments accepted as signal, or ending without an ask.
  • <=3 = a pitch in disguise: leading questions, opinions and fluff, a polite zombie lead, no learning.

Always state the current score out of 7, name the failing diagnostic rows, and give the specific fix for each.

Framework Sections

1. The Mom Test Rules

Core concept: Three rules that make it impossible for even your most supportive loved ones to give you false validation, shifting conversations from opinion-gathering to fact-finding.

Why it works: People are unreliable predictors of their own future behavior, so opinions are worthless. Past behavior is the only reliable data and can genuinely inform product decisions.

Key insights:

  • Rule 1: Talk about their life, not your idea -- never mention your solution until the end, if at all
  • Rule 2: Ask about specifics in the past, not generics or hypotheticals about the future
  • Rule 3: Talk less, listen more -- aim for them to speak 80% of the time
  • A question fails the Mom Test if the answer is always "yes" regardless of whether the business will succeed
  • Good questions could potentially destroy your currently imagined business

Product applications:

ContextApplicationExample
Idea validationAsk about the problem, never the solution"Tell me about the last time you tried to [problem area]" not "Would you use an app that does X?"
Feature prioritizationDiscover what people do vs. what they say"Walk me through how you handled this last week"
Pricing researchAnchor to existing spending behavior"What are you currently paying to solve this?" not "Would you pay $X?"

Copy patterns:

  • "Tell me about the last time you..."
  • "What else have you tried?"
  • "Why does that bother you?"

See: references/question-patterns.md when drafting an interview script -- a 5-tier question hierarchy, domain-specific question banks (SaaS/consumer/marketplace), and four formulation exercises.

2. Good vs Bad Questions

Core concept: Most interview questions are broken because they ask people to predict the future, evaluate hypothetical products, or confirm your assumptions. Good questions anchor in observable past behavior and extract concrete facts.

Why it works: Asking "would you buy this?" is like asking "will you go to the gym next week?" -- the answer is always yes, the follow-through rarely there. Behavior that already happened can't be rationalized away.

Key insights:

  • Bad: "Do you think it's a good idea?" -- always gets a yes
  • Bad: "Would you buy a product that does X?" / "How much would you pay?" -- hypothetical, anchored to please you
  • Good: "How are you dealing with this problem today?" -- reveals actual behavior
  • Good: "What have you tried before and why did you stop?" -- reveals past decisions
  • Good: "Where does the money come from for solutions like this?" -- reveals real budgets
  • The scariest questions -- ones with the power to change what you're building -- produce the most useful data

Product applications:

ContextApplicationExample
Problem validationConfirm the problem exists and matters"When did this last come up? What did you do? What didn't work?"
Market sizingCheck if enough people share the problem"Who else in your industry deals with this? How do they handle it?"
Competitive analysisFind real alternatives already in use"What tools/processes do you currently use for this?"

Copy patterns:

  • "What's the hardest part about [doing this thing]?"
  • "How often does this come up?"
  • "Walk me through what happened the last time this came up"
3. Avoiding Compliments and Opinions

Core concept: Three types of bad data feel like progress but actively mislead: compliments ("That's a great idea!"), fluff (hypotheticals, maybes, future promises), and ideas (feature requests disconnected from real problems). Deflecting these and digging for truth is the core skill.

Why it works: Compliments are the fool's gold of customer development -- they feel amazing but contain zero information about whether anyone will pay or use the product. Only specifics about real past behavior and genuine commitments provide signal.

Key insights:

  • Compliments: deflect immediately and return to concrete facts about how they handle the problem today
  • Fluff: generic claims ("I usually," "I always," "I would never") are worthless without a specific instance
  • Ideas: dig into the motivation behind every feature request -- what's driving it, when they last needed it
  • Fishing for compliments ("Don't you think this would be useful?") is unconscious validation-seeking
  • Symptom of a bad conversation: you walk away feeling great but with no concrete facts or commitments

Product applications:

ContextApplicationExample
Post-demo feedbackDeflect "this looks awesome""Thanks! What part of your current workflow would this replace?"
Feature requestsDig for the underlying job"Why do you want that? Can you show me the last time you needed it?"
Investor conversationsSeparate encouragement from interestAsk for customer intros, not "great idea" feedback

Copy patterns:

  • "Thanks, but to make sure I'm not wasting your time -- what does your current process look like?"
  • "When you say you'd 'definitely' use this, what would you stop using?"
  • "That's a great feature idea -- what problem would it solve for you specifically?"

See: references/avoiding-bad-data.md when a conversation feels good but yields no facts -- how to spot and deflect the three bad-data types (compliments, fluff, ideas) in real time.

4. Commitment and Advancement

Core concept: The currency of a customer conversation is commitment, not compliments. End every conversation with a clear advance toward adoption or a clear rejection -- the worst outcome is a "zombie lead" who is polite but never commits.

Why it works: Saying "I'd definitely buy that" costs nothing; offering an intro, a deposit, or a pilot invests something real. Commitment closes the dangerous gap between what people say and what they do.

Key insights:

  • Commitment currencies: time (meeting, trial), reputation (intro, testimonial), money (deposit, pre-order, letter of intent)
  • Advancing moves the relationship toward a sale; spinning wheels produces pleasant, useless meetings
  • Know your "ask" before the meeting -- the minimum commitment that proves this is real
  • A "no" is more valuable than a "maybe" -- you can learn from it and move on
  • If they won't give you their time, they definitely won't give you their money

Product applications:

ContextApplicationExample
Early validationRequest a commitment that tests interest"Can I follow up with a prototype next week for 15 minutes of your time?"
B2B salesAdvance toward the decision-maker"Could you introduce me to the person who handles the budget for this?"
Pre-launchCollect pre-orders or letters of intent"Launching in 8 weeks -- want to join the first cohort at 40% off?"

Copy patterns:

  • "Who else should I talk to about this?"
  • "Would you be willing to try a prototype next week?"
  • "If I built this, would you be willing to pilot it for 30 days?"

See: references/commitment-advancement.md when a conversation ends without a commitment -- the currency ladder (time/reputation/money) and scripts for advancing instead of spinning wheels.

Show full SKILL.md (990 more words)Show less
5. Finding Conversations

Core concept: The best customer conversations happen casually -- warm intros, industry events, online communities, coffee. Formal "customer interview" framing triggers performance mode; casual framing produces honest data.

Why it works: "Can I interview you about your problems?" makes people polished and guarded; "I'm trying to learn about the industry -- can I buy you coffee?" makes them open up. The framing determines the quality of the data.

Key insights:

  • Cold outreach: keep it short, lead with their expertise, don't pitch
  • Warm intros are the best source -- one well-connected advisor can open dozens of doors
  • Go where customers already gather: industry events, meetups, online communities (participate genuinely first)
  • "I'm trying to learn" beats "I'm doing customer research"
  • Use the five-part structure for getting meetings: vision / framing / weakness / pedestal / ask

Product applications:

ContextApplicationExample
Pre-idea explorationImmerse in the target community3 industry events and 20 casual conversations before writing code
B2B prospectingWarm intros through advisors"Our advisor [Name] suggested I ask how you handle [problem area]"
Consumer researchIntercept at the point of behaviorTalk to people in line at the store, the gym, the coworking space

Copy patterns:

  • "I'm researching how [industry] handles [problem] -- could I learn from your experience over a 15-minute coffee?"
  • "[Mutual contact] suggested I talk to you because you know a lot about [area]"
  • "I'm not trying to sell anything -- I'm just trying to understand the space"

Ethical boundary: Never disguise a sales call as a learning conversation -- if you already have a product and are selling, be transparent.

See: references/finding-conversations.md when you need to source interviews -- cold vs warm outreach templates, the five-part meeting ask (vision/framing/weakness/pedestal/ask), and how to keep it casual.

6. Processing and Learning

Core concept: Conversations are only useful if processed: distill raw notes into beliefs, update them regularly, and share with your team. Without a system you'll cherry-pick quotes that confirm your biases.

Why it works: Memory is biased toward recent and emotionally charged information, so teams selectively remember confirming data. Processing as a team prevents any one person's bias from dominating the narrative.

Key insights:

  • Take notes during or immediately after -- never rely on memory
  • Separate facts (what they said and did) from interpretations (what you think it means)
  • Share raw notes with your team, not filtered summaries
  • Update your three key beliefs after each batch: the problem, the customer segment, the solution
  • Stop talking and start building when conversations start repeating
  • Use a simple spreadsheet: who, date, key quotes, facts, commitments, belief changes

Product applications:

ContextApplicationExample
Team alignmentReview notes together weekly5 conversations per week reviewed as a team; belief board updated
Pivot decisionsTrack evidence against core beliefs8 of 10 conversations reveal a different problem than expected -- pivot
Feature validationCount unprompted mentionsA problem named by 7 of 10 people is real; 1 of 10 might not be

Copy patterns:

  • "Our current belief is X -- here's what confirms it and what challenges it"
  • "We've heard this from N of M people -- is that enough signal?"
  • "Time to stop talking and build -- conversations are repeating"

See: references/processing-learning.md after a batch of interviews -- the notes-to-beliefs spreadsheet template, team-review cadence, and signals that it's time to stop talking and build.

Common Mistakes

MistakeWhy It FailsFix
Pitching your idea instead of asking about their lifeTriggers politeness; produces compliments, not factsDon't mention your idea until the very end, if at all
Asking "would you buy this?"Hypothetical yeses cost nothingAsk what they've already done: "How much are you spending on this now?"
Accepting compliments as validation"Great idea!" carries zero information about behaviorDeflect immediately: "Thanks -- but what are you doing about this today?"
Talking too muchYou learn while listening, not talkingThey should talk 80%+ of the time
No clear ask at the endProduces zombie leads that go nowhereKnow your advance before the meeting: trial, intro, pre-order
Running formal "interview" sessionsTriggers performance mode and filtered answersKeep it casual: coffee, hallway conversations, Slack DMs
Not processing notes as a teamIndividual bias filters data into confirmationShare raw notes weekly; update shared beliefs together

Quick Diagnostic

QuestionIf NoAction
Did the conversation focus on their life and past behavior, not your idea?You ran a pitch, not a Mom Test conversationRedo with zero mention of your solution
Did you get concrete facts about what they've already done?You collected opinions and hypotheticalsAsk about the last time the problem occurred and what they did
Did they give a commitment (time, reputation, or money)?Likely a zombie lead -- polite but not interestedAsk for a specific next step: trial, intro, or pre-order
Did they do most of the talking?You talked too much and learned too littlePractice silence; let awkward pauses work for you
Did you learn something that could change what you're building?You asked safe, confirming questionsAsk the scary questions you've been avoiding
Did you update your beliefs based on the conversation?You're collecting data but not learningReview notes with the team; update problem/segment/solution beliefs
Can you summarize the key facts (not opinions)?Poor notes, or opinions confused with factsSeparate facts from interpretations immediately after

See: references/case-studies.md when you want to see the rules applied end-to-end -- realistic SaaS, consumer, B2B, and marketplace interviews scored against this diagnostic.

Further Reading

This skill is based on Rob Fitzpatrick's Mom Test methodology:

About the Author

Rob Fitzpatrick is an entrepreneur and educator who founded multiple venture-backed startups and learned the hard way that most customer conversations produce misleading feedback. The Mom Test (2013) distills his evidence-based approach, has been translated into 20+ languages, and is required reading at accelerators including Y Combinator and Techstars. He also wrote The Workshop Survival Guide and Write Useful Books.

© wondelai, 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 6 other files (references) in mom-test of wondelai/skills.

  • SKILL.md
  • references/avoiding-bad-data.md
  • references/case-studies.md
  • references/commitment-advancement.md
  • references/finding-conversations.md
  • references/processing-learning.md
  • references/question-patterns.md

Open the folder on GitHubat commit c172996

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.

Mom Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mom Test this skillwondelai/skills2.4k—~4.2kAutomated safety check: PassMIT
User Personasphuryn/pm-skills27k—~762Automated safety check: PassMIT
Product Discoverymajiayu000/spellbook287—~3.3kAutomated safety check: PassMIT
Customer ResearchNexus-JPF/note-companion8706 repos~3.2kAutomated safety check: PassMIT
Opportunity Solution Treeavelikiy/great_cto103—~1.8kAutomated safety check: PassMIT
Customer Interviewsmenkesu/awesome-pm-skills434—~4.4kAutomated safety check: PassCustom licence

Similar skills

  • User Personas

    phuryn/pm-skills

    Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights.

    27k GitHub stars~762 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Product Discovery

    majiayu000/spellbook

    Product discovery and market research expert. An agent skill from majiayu000/spellbook.

    287 GitHub stars~3.3k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Customer Research

    Nexus-JPF/note-companion

    When the user wants to conduct, analyze, or synthesize customer research.

    870 GitHub starsUsed in 6 repos~3.2k tokens
    Marketing & SEOAuto-check passed
  • Opportunity Solution Tree

    avelikiy/great_cto

    Builds an Opportunity Solution Tree that links one measurable outcome to customer opportunities, candidate solutions and experiments.

    103 GitHub stars~1.8k tokensUpdated today
    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
  • Riffrec Feedback Analysis

    EveryInc/compound-engineering-plugin

    Turns Riffrec screen, voice and event recordings into evidence for bug reports and requirements, and helps set up Riffrec when no recording exists yet.

    25k GitHub stars~695 tokensUpdated today
    Product & Project ManagementAuto-check passed

More from wondelai/skills

All 62 skills in this repo
  • Crossing The Chasm

    wondelai/skills

    Navigate the technology adoption lifecycle from early adopters to mainstream market.

    2.4k GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Design Everyday Things

    wondelai/skills

    Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models.

    2.4k GitHub stars~4k tokensUpdated 1 mo ago
    Auto-check passed
  • Design Sprint

    wondelai/skills

    Run a structured 5-day process to prototype, test, and validate product ideas with real users.

    2.4k GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Hooked UX

    wondelai/skills

    Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment).

    2.4k GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Improve Retention

    wondelai/skills

    Diagnose and fix retention problems using behavior design (B=MAP).

    2.4k GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Monetizing Innovation

    wondelai/skills

    Design products and pricing around validated willingness to pay, from Ramanujam & Tacke's "Monetizing Innovation".

    2.4k GitHub stars~5.2k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Mom Test

What does Mom Test do?

Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less. Mom Test is an agent skill from wondelai/skills. Talk to customers without leading them using Mom Test rules: discuss their life not your idea, ask about specifics in the past, and talk less.

When should I use Mom Test?

Mom Test fits situations like: the user mentions customer interviews; validate my idea; users say they want it but dont buy; leading questions.

How do I install Mom Test in Claude Code?

Run `npx skills add wondelai/skills --skill mom-test -a claude-code`. Or copy the skill folder (mom-test in wondelai/skills) 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 wondelai/skills --skill mom-test -a codex`. Or copy the skill folder (mom-test in wondelai/skills) 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 wondelai/skills --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 names 1 domain. As links in the text: amazon.com. 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 (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mom Test use?

About 4.2k tokens (SKILL.md is roughly 17k 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 19k tokens, read only when the agent opens those files.

What are the alternatives to Mom Test?

Skills that share tags, products or a category with Mom Test: User Personas (phuryn/pm-skills, 27k stars), Product Discovery (majiayu000/spellbook, 287 stars), Customer Research (Nexus-JPF/note-companion, 870 stars) and Opportunity Solution Tree (avelikiy/great_cto, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mom Test?

wondelai (a GitHub organization) maintains it in wondelai/skills, which has 2,371 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on September 10, 2026.

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