Validate Idea
Pressure-test a business idea with a sell-first, build-later checklist before you ship code or spend on infra.
Overview
validate-idea is an agent skill for the Validate phase that guides solo builders through sell-first, problem-first checks before they build or spend.
Install
npx skills add https://github.com/slavingia/skills --skill validate-ideaWhat is this skill?
- Frames validation as selling a manual solution first, not shipping software
- Forces precise ICP definition and documents today's workarounds as real competition
- Walks through processizing—manual delivery you can later automate
- Channels Minimalist Entrepreneur principles (problem-first, hair-on-fire pain test)
- Blocks months of build-on-assumption by requiring paid-intent signals upfront
- Core validation principle: sell before you build
- Step 1 focuses on problem definition with four diagnostic questions
Adoption & trust: 857 installs on skills.sh; 9.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are excited about an idea but have no proof that a specific audience will pay to make the pain go away.
Who is it for?
Solo founders with a raw idea who need structured validation conversations and manual-offer experiments before writing code.
Skip if: Teams that already have recurring revenue, an approved spec, or who only want technical architecture planning without customer discovery.
When should I use this skill?
Someone has a business idea and wants to test if it is worth pursuing before building anything.
What do I get? / Deliverables
You leave with a sharper problem statement, manual validation path, and a clearer decision to pursue, pivot, or stop before implementation.
- Sharpened problem and ICP definition
- Manual validation / processizing plan
- Go, pivot, or stop recommendation with next experiments
Recommended Skills
Journey fit
Idea validation belongs on the Validate shelf because the skill explicitly targets proving demand before any product build. Scope is the right subphase: it narrows who has the problem, pain, and willingness to pay—not landing-page polish or final pricing tables alone.
How it compares
Use for customer-discovery validation instead of jumping straight into implementation-plan or coding skills.
Common Questions / FAQ
Who is validate-idea for?
Solo and indie builders with a business hypothesis who want advisor-style prompts to test demand before building product.
When should I use validate-idea?
In Validate when you need to scope the problem, test willingness to pay, or design a manual concierge offer; also early in Idea research when deciding whether to commit to a build.
Is validate-idea safe to install?
It is advisory prose with no declared tool execution; review the Security Audits panel on this Prism page before installing any skill from the registry.
SKILL.md
READMESKILL.md - Validate Idea
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