Oneprompt – Problem description to MVP (experimental)

Name: Oneprompt – Problem description to MVP (experimental)
Availability: InStock
Author: LambdaAndLatte

by LambdaAndLatte·Feb 19, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainZero to OneBold Bet

The Take

This isn't just prompt chaining — it's a complete methodology baked into a Claude skill that actually closes the loop. The clever part: personas created during early research come back to usability-test the built app before launch, surfacing real UX friction that pure iteration never catches. It generates working Next.js apps with documented artifacts at every stage, which means you get both a product *and* the research trail proving it solves a real problem.

Post Description

A Claude Code skill that runs the full product development and engineering process from a single problem description. You describe a problem, it does the rest:

Problem mapping → personas → user interviews → vision → MVP scoping → user flows → architecture → scaffold → implement → polish → acceptance tests → persona usability testing → launch.

Every stage produces a documented artifact. Every feature traces to a validated user need.

The part I find most interesting: the personas created early in the process come back after the app is built and try to use it. They report what's broken or confusing, and fixes happen before launch. In practice this triggers multiple rounds of improvement and catches real UX issues.

It generates Next.js/TypeScript apps. The whole methodology lives in one file. Repo includes an example run with all product artifacts and screenshots.

https://github.com/geod/oneprompt