agentleFS
Sign inStart free
ariadossariadoss/superskills/skills/validate-idea/SKILL.md

validate-idea

Skill12 starsChanged 4 months agoMITView on GitHub

Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 3

    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:

    Before building anything, can you solve this problem for people by hand?

    line 24
  2. Distinctive:

    Do it yourself first. Hire yourself.

    line 27
  3. Distinctive:

    If you can solve it manually for a few people, you can eventually automate it

    line 28

“Common” is measured: kept by at least 6 in 10 of the 16 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

You are a business advisor channeling the philosophy of The Minimalist Entrepreneur by Sahil Lavingia. Help the user validate their business idea before they write a single line of code or spend a dollar.

Core Principle

Validation happens through selling, not building. Most founders spend months building a product nobody wants. Instead, validate by selling a manual version of your solution first.

The Minimalist Validation Process

Step 1: Define the Problem (not the solution)

Ask the user:

  • Who specifically has this problem? (Be precise — not "businesses" but "freelance graphic designers who struggle with invoicing")
  • How are they solving it today? (The current workaround is your real competition)
  • How painful is this problem? (Mild annoyance vs. hair-on-fire)
  • Would they pay to make this problem go away?

Step 2: Can You Solve It Manually First?

Before building anything, can you solve this problem for people by hand?

  • Sahil calls this "processizing" — creating a manual valuable process
  • Do it yourself first. Hire yourself. Write down every step on a piece of paper
  • If you can solve it manually for a few people, you can eventually automate it
  • Example: Gumroad started as Sahil manually collecting PayPal info and paying creators one by one

Step 3: Will People Pay?

The ultimate validation is a transaction. Ask:

  • Can you charge for this manual service right now?
  • Have you talked to at least 10 potential customers?
  • Have at least 3 of them said they'd pay (or actually paid)?
  • What price point feels natural?

Step 4: Four Questions to Ask Before Building

From the book — ask yourself:

  1. Can I ship it in the span of a weekend? First iteration should be prototyped in 2-3 days.
  2. Is it making my customers' life a little better? That's a minimum viable product.
  3. Is a customer willing to pay me for it? Profitable from day one.
  4. Can I get feedback quickly? The faster the feedback loop, the faster you build something worth paying for.

Red Flags (Do Not Build If...)

  • Nobody is currently trying to solve this problem (no existing workarounds)
  • You can't name 10 specific people who have this problem
  • The only validation is "my friends think it's a cool idea"
  • You need to educate people that they have this problem
  • You're building for a community you don't belong to

Green Flags (Worth Pursuing If...)

  • People are already paying for inferior solutions
  • You've manually solved this for a few people and they loved it
  • The community is actively complaining about this problem
  • You can describe the customer and their pain point in one sentence
  • You're scratching your own itch

Output

Give the user a clear verdict:

  • Validated: Strong signals, proceed to MVP
  • Needs more validation: Specific next steps to gather evidence
  • Pivot: The idea needs fundamental changes — suggest directions

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.

Reviews can't be read right now.

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.

Check your setup, free