agentleFS
scaccogattoscaccogatto/minimalist-entrepreneur/skills/mvp/SKILL.md

mvp

Skill1 starsChanged 8 months agoMITView on GitHub

Guide building a minimum viable product the minimalist entrepreneur way — manual first, then processized, then productized. Use when someone is ready to build their first product, struggling with scope, or over-engineering. Also use when the user mentions "MVP," "minimum viable product," "what to build first," "scope creep," "ship fast," or "launch weekend." For validating the idea first, see validate-idea. For turning it into a manual process, see processize.

11 other projects use a version of this, 5 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write down every step you take — this becomes your process

    line 25
  2. Distinctive:

    Document your process on a piece of paper so anyone could do it

    line 29
  3. Distinctive:

    If you go on vacation, someone else can take over

    line 30
  4. Distinctive:

    Only build what you've already proven works manually

    line 37
  5. Distinctive:

    Before building anything, answer:

    line 41
  6. Distinctive:

    Can I ship it in a weekend?: If not, reduce scope until you can.

    line 42
  7. Distinctive:

    Use existing tools: Use Carrd, Gumroad, Stripe, Airtable, Google Forms, Zapier, Notion — whatever gets you to market fastest.

    line 55
  8. Distinctive:

    Don't build features you think you'll need "someday"

    line 59
  9. Distinctive:

    Don't build for scale — you don't have scale problems yet

    line 60
  10. Distinctive:

    Don't build a mobile app when a website works

    line 61
  11. Distinctive:

    Don't write code when a spreadsheet works

    line 62
  12. Distinctive:

    Don't hire an engineer when you can use no-code tools

    line 63

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Guide the user through building their MVP with maximum constraints and minimum effort.

Core Principle

Build as little as possible. The goal is to start delivering value to your community as quickly as possible. Not to build something beautiful, polished, or complete.

The Three Stages

Stage 1: Manual (Do it yourself)

  • Solve the problem by hand for each customer
  • You are the product. You are customer service, fulfillment, and engineering
  • Write down every step you take — this becomes your process
  • Example: Before Gumroad automated payouts, Sahil collected PayPal emails and sent payments manually, one by one

Stage 2: Processized (Systematize the manual work)

  • Document your process on a piece of paper so anyone could do it
  • If you go on vacation, someone else can take over
  • You've built a system for working efficiently with each customer
  • This is your "magic piece of paper"

Stage 3: Productized (Automate the process)

  • Now automate each task so customers can use your product without you
  • This is when you actually build software or a product
  • Only build what you've already proven works manually

The Four Build Questions

Before building anything, answer:

  1. Can I ship it in a weekend? If not, reduce scope until you can.
  2. Is it making my customers' life a little better? That's the bar for MVP.
  3. Is a customer willing to pay for it? Be profitable from day one.
  4. Can I get feedback quickly? Build for people who can tell you if it's working.

What to Build

Most apps on the internet are just forms and lists (CRUD: Create, Read, Update, Delete). Your MVP should be no more complex than that.

For your MVP:

  • One thing. Your product does one thing, at first.
  • No polish. It doesn't need to be pretty. Craigslist has never been pretty.
  • Charge money. There's a huge difference between free and $1 (the zero price effect). Charge something.
  • Use existing tools. Use Carrd, Gumroad, Stripe, Airtable, Google Forms, Zapier, Notion — whatever gets you to market fastest. Every business is tech-enabled now.

What NOT to Build

  • Don't build features you think you'll need "someday"
  • Don't build for scale — you don't have scale problems yet
  • Don't build a mobile app when a website works
  • Don't write code when a spreadsheet works
  • Don't hire an engineer when you can use no-code tools

Ship Early and Often

  • You will be wrong. The goal is to get less wrong as quickly as possible
  • Gumroad has never shipped a "v2" — just thousands of incremental improvements over many years
  • Each time you ship, you cross the threshold from "I may want this later" to "I need this now" for some customer
  • Your goal is to move away from being paid directly for your time

Essentials Checklist

Before you launch:

  • Name your business (two real words combined > made-up word; pass the "radio test")
  • Buy a domain (~$10/year)
  • Build a simple website (Carrd, Gumroad, or similar)
  • Create social media accounts (personal + business)
  • Set up payments (Stripe or Square — 2.9% + 30c per transaction)
  • Create an email for customer communication

Output

Help the user define:

  1. The single thing their MVP does
  2. The simplest possible implementation (manual, no-code, or minimal code)
  3. What they can ship this weekend
  4. Their initial price point
  5. How they'll collect feedback

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.