vibe-coding

refoundai/lenny-skills

Build functional software through natural language with AI coding tools—no deep technical skills required.

What is vibe-coding?

Vibe coding is the skill of iteratively building working software by conversing with AI tools, breaking problems into smaller pieces, and refining outputs through follow-up prompts. Use it when prototyping quickly, validating ideas without engineers, or exploring how non-technical roles (PMs, designers, marketers) can create functional tools.

Break down complex problems into smaller, iterative AI prompts for incremental builds
Guide users through testing and refining AI-generated code rather than assuming it works
Help distinguish when vibe coding is appropriate (prototypes, MVPs, internal tools) versus when professional engineering is needed
Coach on iterative refinement—asking follow-up questions and describing what's not working to improve output
Replace static mockups with functional prototypes built in 30 minutes to demonstrate proofs of concept

How to install vibe-coding

npx skills add https://github.com/refoundai/lenny-skills --skill vibe-coding

Claude Code

Cursor

Windsurf

Cline

How to use vibe-coding

1.Clarify what you're building and who will use it—prototype, internal tool, or production app
2.Break down the problem into smaller, manageable pieces rather than trying to build everything at once
3.Write clear, descriptive prompts to the AI tool describing what you want
4.Run and test the generated code immediately; don't assume it works
5.Iterate by describing what's not working and asking the AI to refine it
6.Know when to stop—vibe-coded software is great for validation but may need professional engineering for production

Use cases

Good for

A PM wants to validate a product idea by building a working prototype in an afternoon instead of waiting for engineering
A marketer needs a quick internal tool to process data without hiring developers
A designer builds a custom animation editor to test interaction patterns before handing off to engineers
A founder explores multiple product directions by rapidly vibe-coding different MVPs to test with users
A non-technical founder builds the first version of their app to demonstrate to investors

Who it's for

Product managers exploring ideas without engineering resources
Designers and marketers building internal tools or prototypes
Founders and entrepreneurs validating concepts before scaling
Non-technical team members who want to build functional software
Anyone prototyping or building MVPs with tight timelines

vibe-coding FAQ

Is vibe coding just prompt engineering?

No. Vibe coding is iteratively building functional software through conversation with AI, which requires breaking problems down, testing outputs, and refining through follow-up. Prompt engineering is just one part of the skill.

When should I use vibe coding versus hiring engineers?

Use vibe coding for prototypes, MVPs, internal tools, and validation. For production-grade systems with complex requirements, scaling needs, or security concerns, professional engineering review is essential.

How long does it take to vibe code something?

Simple prototypes and proofs of concept can be built in 30 minutes to a few hours. More complex tools may take longer, but the goal is speed and iteration, not perfection.

What if the AI output doesn't work?

Test it immediately, describe what's broken or missing, and ask the AI to fix it. Vibe coding is iterative—refine through follow-up prompts rather than giving up after one try.

Can I use vibe-coded software in production?

Vibe-coded software can go to production for internal tools and simple applications, but complex systems should have professional engineering review for reliability, security, and scalability.

Full instructions (SKILL.md)

Source of truth, from refoundai/lenny-skills.

name: vibe-coding description: Help users build software using AI coding tools. Use when someone is using AI to generate code, building prototypes without deep technical skills, or exploring how non-engineers can create functional software through natural language.

Vibe Coding

Help the user build software using AI tools and natural language, using frameworks and insights from 3 product leaders.

How to Help

When the user asks for help with vibe coding:

Understand the goal - Ask what they're trying to build and who it's for (prototype, internal tool, production app)
Guide the approach - Help them break down the problem into smaller pieces for iterative AI prompts
Set expectations - Discuss what vibe coding is good for (prototypes, MVPs) versus when professional engineering is needed
Coach on iteration - Help them understand how to refine output through follow-up prompts

Core Principles

Vibe coding is a new skill

Elena Verna: "I vibe code myself so I would put that as even as a skill on my resume now." This is a distinct, transformative skill for non-technical roles - PMs, marketers, designers - to build functional software using natural language.

Replace Figma with prototypes

Kevin Weil: "Instead of showing stuff in Figma, we should be showing prototypes that people are vibe coding over the course of 30 minutes to illustrate proofs of concept." Functional code prototypes can be built in the time it takes to create static mockups.

Build tools to build tools

Alexander Embiricos: "They'll vibe code an animation editor and then they use the animation editor to build the animation." Non-engineers can now build functional software and custom tools without deep technical mastery.

Go beyond prompt engineering

Vibe coding is not just writing prompts - it's iteratively building functional software through conversation with AI. It requires understanding how to break problems down, test outputs, and refine through follow-up.

Know the limits

Vibe-coded software is great for prototypes, internal tools, and MVPs. Production-grade systems with complex requirements still need professional engineering review.

Questions to Help Users

"What are you trying to build, and who will use it?"
"Is this a throwaway prototype or something that needs to scale?"
"Can you break this down into smaller pieces to build incrementally?"
"What's the simplest version that would let you test your hypothesis?"
"Have you tried describing what's not working and asking the AI to fix it?"
"Do you need this to be production-grade, or is it okay if it's rough?"

Common Mistakes to Flag

Trying to build everything at once - Break complex projects into smaller, iterative builds
Not testing the output - Always run and test what the AI generates; don't assume it works
Expecting production quality - Vibe-coded apps are great for validation but may need engineering for production
Unclear specifications - The clearer your description of what you want, the better the output
Giving up after one try - Vibe coding is iterative; refine through follow-up prompts