Vibecoding
Build for the vibe, debug later
Start new thread
Aaron O'Leary

Prompt recipes: from boilerplate to production

by

AI coding is pretty mindblowing but sometimes it's a headache built on a mountain of bugs. Usually that comes down to issues with how you prompt. So, with that in mind, I'm starting a crowdsourcing discussion so we can all improve our prompts and in turn our apps.

Share the exact prompts that turn blank AI requests into real‑world code. Show us how you go from “generate a REST API” to a deployable service in just a few steps.

What to post:

  • Prompt text (copy‑&‑paste ready) and its purpose (e.g., Node + Express, React, Python/FastAPI).

  • Key tweaks: how you layered in error handling, authentication, database setup, tests, Docker, CI/CD, etc.

  • Parameter files: JSON/YAML examples you feed in to auto‑generate endpoints, configs, or components.

Bonus points:

  • A single prompt that reads a JSON spec (e.g., service name, endpoints, DB choice) and spins up an entire project.

  • A chain of prompts covering frontend → API client → backend → deployment script.

Let’s build a lean, battle‑tested cookbook of prompts anyone can copy, tweak, and ship!

1.4K views

Add a comment

Replies

Best
Gabe Perez

Okay so while not vibe coding this is my favorite prompt to use on @Krea to get some good images for my projects.

Dark underexposed and extremely elegant photo of [SUBECT] floating out of balance in mid air on a [COLOR] to [COLOR] gradient background, highly saturated high contrast background, almost glowing, product photography, extremely elegant, studio lighting, minimalist composition, simple background, shot on Canon EOS R5, extremely clear, extremely sharp, crisp, close up, 8k, gradient background, ultra crisp, high key lighting, professional color grading

For Vibe coding, it really depends on the language but for Swift I try to break it up by file type and so my first prompt to an LLM usually goes something like [Enter app's desired goal/function/utility] and build me a step-by-step guide on how to build it. Break down each step by the files needed for it, the file types, and what the do. Make each step a phase. Lets have no more than 5 phases total.

Then what I do is I put those phases into a README, take that README into Cursor, give it the same prompt I gave the LLM, then tell it to refer to the README, then have it list out anything it might think on how to improve the process, if so, to update the README. So that prompt is like:

[Enter app's desired goal/function/utility] and plan a step-by-step guide on how to build it. Break down each step by the files needed for it, the file types, and what the do. Make each step a phase. Lets have no more than 5 phases total.

Analyze @README file for our current structure. Critique it. Improve it and update the README with our final, new and improved plan with 5 phases.

Once it updates the README I tell @Cursor to then:

Look at the @readme and build out an action plan/todo list of how we're going to complete phase 1. Once you have it built, start building and implementing it for me. Only ask me to interject if I need to personalize some sort of language, function, or user experience.

From there I rinse and repeat until I finish all the phases.

This way I can

  • Debug easier (per phase)

  • Save my repo accordingly and revert back to changes easier (Phase 2 messed up what we had? No problem, Phase 1 is sae)

  • Helps the LLM zone in on a specific context and focus so it's less likely to make mistakes

  • The README helps give it continuous context of where we came from and where we're going for

Aaron O'Leary

@gabe this was super informative! I like the idea of limiting the phases, for me a big issue, is AI forgets halfway through what it's building if it has a long build process.

Jakomi Mathews

@README  @gabe Whilst not a coder any more I also like this and get the process and may try it myself over the coming days - many thanks!

Deft Clay

@README  @gabe 

In line with what you are doing here having @Cursor make a plan, check out this video. It's worth a watch. You download a custom instructions file from Git, and use that and a few simple questions to come up with the app's overall task list, then @Cursor breaks it into subtasks with check boxes, and you work your way through the file.

https://www.youtube.com/watch?v=cniTWVMGD08&list=LL&index=1

How Vibe Coding Goes PRO

steve beyatte

I basically mind dump into Grok 4 and tell it to ask me clarifying questions until it can write an effective prompt to build X. Then I put that into Claude Code or Windsurf. I can't be bothered to use my brain to write the real prompt, that's what the robot is for.

Aaron O'Leary

@steveb thats a smart move! i like that!

Frederik Bussler

For me, the initial prompt isn't everything - AI can still go off the rails with a great prompt. But I've found that when it's not doing well, it's good to clear the context (e.g. fork everything into a new chat), or you'll keep having the same issue. It's like giving the AI a clean slate / fresh perspective, without the context of failure.

Aaron O'Leary

@frederikb yeah, i've found that too. it's like it gets overwhelmed sometimes

Frederik Bussler

@aaronoleary great way to put it! feels almost human sometimes

KAJ Analytics
Great question. Having a lot of Software Dev Experience is a big weight factor for this. Vibe coding is really cool but can run off the rails if do not have great software design principles and understand design patterns.
Hans

The best results I've found come from "crossing the streams," so to speak. As others mentioned, to take a spec from one GPT and apply it with another. I've found that breaking things into fine chunks, ideally "hopped" between GPTs, provides dramatically decreased errors, and increased end-to-end function.

Ilai Szpiezak

Hey! So I’m very involved in the Vibe Coding world and prompt engineering (or as it’s called now “context engineering “!)

And built a tool that basically helps with all the issues with prompting. It’s called Pretty Prompt and works like Grammarly, but for prompting.

I’d love to hear feedback from the community if anyone has tried with different prompting techniques.

Christopher Robbins

@aaronoleary I actually built an app to do just this, sorta - I'll give an example on a public repo. You can export these as JSON too!

I'm gearing up to launch here on product hunt very soon!! Keep an eye out for initepo

Example project : https://github.com/initrepo/venturepilot-ai

Example Description: VenturePilot AI is a SaaS platform providing founders with comprehensive, AI-driven market intelligence and validation reports. It empowers data-backed decisions by analyzing startup ideas against market trends, competitor landscapes, and potential customer pain points, significantly de-risking the entrepreneurial journey from ideation to MVP.

Inside the repo: you will get documentation that you can feed any ai coding platform, just prompt "Please Build VenturePilot AI" and it should get to building. Your tool will let you know when it needs your help for setting up 3rd party services for auth, hosting and other API's - You can simply tell it to build everything with easy find/replace words.