Product Vision logo

Product Vision

OrganizationPopular
RefoundAI
product-vision

Help users define a compelling, qualitative description of a future state that aligns decentralized teams and motivates long-term innovation.

Overview

PublisherRefoundAI
Repositorylenny-skills
Skill nameproduct-vision
Stars
1.4K
Forks
175
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 Product Vision 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.
    https://github.com/RefoundAI/lenny-skills/tree/main/skills/product-vision
  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/product-vision .claude/skills/product-vision
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product Vision 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 Product Vision 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 Product Vision 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.

Product Vision Creation

Design an aspirational future state that inspires teams and guides strategic decision-making.

Help the user with product vision creation using insights from 22 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Define the Destination - Guide the user in articulating a lofty yet realistic future state grounded in a potent user problem.
  2. Craft the Narrative - Help translate technical goals into an emotional metaphor or a strategic narrative that resonates with human psychology.
  3. Visualize the Outcome - Advise on creating visual prototypes or storyboards that make the abstract vision concrete for stakeholders.
  4. Connect to Execution - Facilitate the process of working backward from the ideal future to create a tactical multi-year roadmap.

Core Principles

Use Emotional Metaphors

Ami Vora: "If we all agree that the feeling of something should be, I'm sitting in Dolores Park with my friends on a sunny Saturday, then people will just naturally build something that feels more consistent."

Establish a shared emotional metaphor to guide decentralized teams toward consistent decision making without constant oversight.

Ground Vision in Potent Problems

Ebi Atawodi: "So four things. So it has to be lofty, it has to be realistic, it has to be devoid of any tech or limitations of today, and it has to be grounded in a very clear and potent problem. User problem."

Ensure the vision is rooted in a clear and significant user problem that the team feels personally motivated to solve.

Synthesize Across Functions

Mihika Kapoor: "You want to always ensure that there are research insights that help you feel what a user is feeling. You want to ensure that there are beautiful designs and prototypes that help communicate what this future world looks like, and you also want to root it in engineering and feasibility. And you want to be constantly, even in the vision phase, assuring that what you're marching after is something that is achievable and something that you can work towards."

A compelling vision must be a cross-functional blend of deep user empathy, technical feasibility, and visual storytelling.

Balance Art with Science

Sanchan Saxena: "If you become too scientific, you miss out on opportunities because you can't see those opportunities using the scientific method of discovery, because they're too tiny or they're so farfetched that people cannot even understand them."

Avoid over-reliance on scientific methods and A/B testing to prevent missing out on far-fetched or nascent product opportunities.

Unify with a Strategic Narrative

Andy Raskin: "The one thing I say is it's this one story that the CEO uses to drive success in marketing, sales, but also product. That it becomes like a north star, strategic north star for product roadmap, for fundraising, for recruiting, really everything."

Develop a single high-level story that acts as a North Star to align every department from sales to engineering.

Default to Large-Scale Thinking

Shreyas Doshi: "Google, I think the main thing I learned was the power of thinking really big. And I know it sounds like a platitude, but really big. And I only actually realized that when I left Google and I started working with the other teams and these were all capable teams and I was struck by how many teams just limited the potential of what they could achieve."

High-performing cultures prevent teams from setting artificial limits by making large-scale thinking a default operating habit.

Templates & Frameworks

  • Column A vs. Column B Thinking (Melanie Perkins) - A mental model for strategic planning. Column A is looking at the resources (bricks) you have today and seeing what you can build. Column B is imagining the per
  • The 10-Star Experience Framework (First-principles thinking) - Brian Chesky's thought experiment for designing extraordinary customer experiences by imagining progressively more extreme versions and then reverse-engineering
  • Three-Year Painted Picture (How Miro builds product) - A high-level, bold, and ambitious vision document co-developed by the Leadership Team that defines outcomes for users and the company over three years
  • Amazon PRFAQ (Press Release & FAQ) (Jason Shah) - A document written before building a product to clarify the vision, customer value, and rollout plan.
  • Airbnb Snow White Storyboard Project (What Seven Years at Airbnb Taught Me About Building a Business) - How Airbnb used Disney-inspired storyboards to map the ideal guest and host experience, identifying key emotional moments and strategic gaps.
  • WhatsApp 'Face-to-Face' Metaphor (Ami Vora) - An example of using an emotional metaphor to drive decentralized product design decisions.
  • Roman Pichler's Product Vision Board (My favorite product management templates) - A structured canvas for articulating product vision including target group, needs, product, and business goals
  • Concept Car Prototyping for Long-term Strategy (Strategy Blocks: An operator’s guide to product strategy) - An approach to generating exploratory prototypes for long-term strategy that are not intended to be production-ready but spark inspiration and identify winning

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

Questions to Help Users

  • "What specific feeling do you want users to experience when they interact with your product?"
  • "If all technical and operational constraints were removed, what would a 15-out-of-10 experience look like?"
  • "What is the potent user problem that makes this vision necessary right now?"
  • "What does the world look like after your mission is successful in ten years?"
  • "Can you describe your product's destination using a non-technical analogy?"
  • "What are the non-negotiable strategic shifts that must happen to achieve this vision?"

Common Mistakes to Flag

  • Incremental Strategic Drift - Teams often focus on short-term resource availability rather than defining an ideal future state and working backward.
  • Over-Reliance on Data for Vision - Strict adherence to scientific methods can cause leaders to miss nascent opportunities that require artistic intuition.
  • Text-Heavy Vision Documents - Lengthy text-based descriptions are harder to consume and align on compared to visual prototypes and vivid storytelling.
  • Disconnecting Vision from Daily Tasks - Sustained motivation is lost when employees cannot see a clear link between their immediate work and the company mission.

Deep Dive

For all 20 sourced insights from 22 guests, see references/guest-insights.md

Related Skills

  • Defining Product Strategy
  • Positioning
  • Pricing Strategy
  • North Star Metrics

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 Product Vision AI skill do?

Help users define a compelling, qualitative description of a future state that aligns decentralized teams and motivates long-term innovation.

Why use Product Vision on TypingMind?

Because you install it once and use it with any model. Product Vision 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 Product Vision in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RefoundAI/lenny-skills/tree/main/skills/product-vision. 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 Product Vision?

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 Product Vision?

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

Is the Product Vision 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 👇