Idea Validation logo

Idea Validation

OrganizationPopular
RefoundAI
idea-validation

Help users de-risk new product bets by testing core assumptions, building low-fidelity prototypes, and gathering high-signal evidence before investing heavy engineering resources.

Overview

PublisherRefoundAI
Repositorylenny-skills
Skill nameidea-validation
Stars
1.3K
Forks
170
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by RefoundAI on GitHub. Read the source before you install it.

Installation

Install the Idea Validation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git /tmp/lenny-skills
mkdir -p .claude/skills
cp -r /tmp/lenny-skills/skills/idea-validation .claude/skills/idea-validation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Idea Validation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Idea Validation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Idea Validation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Idea Validation

Stop building things people don't want by moving from opinion to evidence-based development.

Help the user with idea validation using insights from 31 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Clarify the Core Hypothesis - Help the user define the specific problem, target audience, and the most 'risky' assumptions using the Founding Hypothesis Scorecard.
  2. Select a Validation Path - Guide the user through choosing between the 'Listening Path', 'Manual Path', or 'Self-Serve Path' based on their proximity to the problem.
  3. Design Low-Fidelity Experiments - Recommend specific 'Wizard of Oz' or 'Fake Door' tests to simulate the solution without building a backend.
  4. Evaluate Signal Quality - Help users distinguish between polite interest and real market pull by looking for financial commitment or high-effort usage.

Core Principles

First-Principles De-risking

Bangaly Kaba: "Someone says, 'Hey, you know what? This would be great to build.' And you go pull data to go justify why that would be great to build. Call that identify, justify, execute. First you have to really understand from first principles what is actually going on."

True de-risking starts with understanding the core problem from first principles before looking for data to justify a specific solution.

Maintaining Prototype Momentum

Grant Lee: "We would have an idea in the morning, come up with some sort of functional prototype, recruit a bunch of people that are legitimately good prospective users, but have zero skin in the game, ship fast so people can start playing with it. In the afternoon, we're already running pretty full scale experiment."

Build functional prototypes within hours of conceiving an idea to maintain speed and identify usability flaws before wasting development cycles.

Direct User Feedback Loops

Gustaf Alstromer: "If I drill down what makes companies fail, it's quite simple. It's just like they don't talk to users, which means they don't find product market fit. And if they don't find product market fit, nothing else really matters."

Achieve product-market fit by talking to customers directly and immediately to learn if you are building something people actually want.

Workflow Compression

Oji Udezue: "So the zone of benefit works as a framework because people will not pay for things that don't either really shrink the workflow that they're doing or doesn't give them superpower. So the same amount of time, but twice as much output. But the most important thing is that it has to be noticeable."

A problem is only worth building for if your solution offers a visible and massive compression of the existing customer workflow.

Templates & Frameworks

  • Four B2B Idea Validation Paths (How to validate your B2B startup idea) - A framework for choosing which validation strategy to use based on your context as a founder. Each path represents a different level of up-front investment and
  • B2B Idea Validation Interview Process (How to validate your B2B startup idea) - A synthesized process for conducting validation interviews based on patterns across multiple successful B2B founders
  • Four Signs Your B2B Idea Has Real Pull (How to validate your B2B startup idea) - A checklist of signals that indicate genuine market demand vs. polite but hollow interest
  • Vanta's Manual Validation Process (How to validate your B2B startup idea) - How Christina Cacioppo validated Vanta's idea by manually creating SOC 2 compliance reports before writing any code
  • Founding Hypothesis Scorecard (Introducing the Foundation Sprint: From the creators of the Design Sprint) - A scorecard with testable questions for each element of the Founding Hypothesis, used to systematically validate or invalidate your product strategy
  • Pre-Product Invoice Test (How to know if you've got product-market fit) - A pre-product PMF validation technique where you literally try to get potential customers to pay you before the product exists.
  • Ugly Baby Validation (1,000,000) - A framework for getting early validation on a new creative project by finding the right motivators
  • DoorDash's paloaltodelivery.com MVP (How the biggest consumer apps got their first 1,000 users) - How DoorDash validated demand with a simple website with PDF menus and printed flyers at Stanford

See references/artifacts.md for the full list with details.

Questions to Help Users

  • "What is the single most risky assumption that must be true for this idea to succeed?"
  • "Are you getting feedback from cold prospects or just people in your network who want to be nice?"
  • "How many steps does your solution remove from the user's current manual workflow?"
  • "If you had to launch a 'fake door' experiment tomorrow with zero backend, what would it look like?"
  • "Has a potential customer offered to pay for this before you have even built it?"
  • "What is the 'must-have' feature that, if missing, would cause the user to walk away immediately?"

Common Mistakes to Flag

  • Confusing Politeness with Validation - Mistaking 'this looks cool' for 'I will pay for this' leads to building products that lack real market pull.
  • Building Before Testing - Investing heavy engineering resources into a full backend before validating the front-end value proposition wastes months of time.
  • Relying on Warm Leads - Feedback from friends or family is biased and rarely provides the 'pure' signal needed to judge an idea's merit.
  • Averaging User Feedback - Failing to segment feedback between skeptics and early adopters can lead to a watered-down product that serves nobody well.

Deep Dive

For all 33 sourced insights from 31 guests, see references/guest-insights.md

Related Skills

  • Customer Interviews
  • Continuous Discovery
  • Product Experiments
  • Defining Icp

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Idea Validation AI skill do?

Help users de-risk new product bets by testing core assumptions, building low-fidelity prototypes, and gathering high-signal evidence before investing heavy engineering resources.

Why use Idea Validation on TypingMind?

Because you install it once and use it with any model. Idea Validation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Idea Validation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RefoundAI/lenny-skills/tree/main/skills/idea-validation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Idea Validation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Idea Validation?

As many as you like. As long as a model supports skills, you can use Idea Validation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Idea Validation AI skill free?

Yes. It is published on GitHub by RefoundAI under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇