npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@ui-construction-library/prompt-engine

v0.1.3

Published

Internal AI prompt generation engine for @ui-construction-library tooling — not for direct consumer use.

Readme

@ui-construction-library/prompt-engine

INTERNAL-ONLY: This package is not part of the public API surface.

Deterministic prompt-to-UI draft generation for builder-compatible projects.

Status

Current maturity: experimental / platform-ready.

This package is intended to convert structured prompt input into builder-compatible draft projects with deterministic behavior, explicit safety rails, validation, repair, and explainability metadata. It is currently suitable as an internal platform subsystem and integration surface for the builder app, but it should not yet be treated as a broadly stable public API.

Responsibilities

  • Accept structured prompt requests.
  • Choose a deterministic generation mode.
  • Produce builder-compatible draft project output.
  • Validate generated drafts against schema-required shapes.
  • Repair common invalid draft structures.
  • Surface explainability metadata such as assumptions, alternatives, recipe identifiers, and used components.

Current public surface

Primary concepts currently exposed by the package:

  • PromptRequest
  • PromptResponse
  • PromptGenerationMode
  • NormalizedPromptRequest
  • PromptDraftReviewSummary
  • PromptRecipeSummary
  • normalizePromptRequest()
  • generatePromptDraft()
  • validatePromptDraftProject()
  • repairPromptDraftProject()
  • toBuilderCompatibleProject()
  • getPromptGenerationSafetyRails()
  • summarizePromptResponse()
  • summarizePromptRecipe()

Design goals

  • Deterministic output for the same structured input.
  • Builder-first compatibility over freeform AI output.
  • Safe degradation with explicit diagnostics and repair behavior.
  • Explainability strong enough to support product UI and future governance features.

Non-goals

  • Freeform LLM orchestration.
  • Pixel-perfect visual design generation.
  • Runtime-specific app generation.
  • Final export rendering.
  • Replacement for builder editing or export validation.

Current limitations

  • Generation modes are intentionally narrow.
  • Output recipes are still baseline and deterministic-first.
  • The package is optimized for internal integration, not yet for wide external consumption.
  • Broader section-repair and multi-step regeneration workflows are still future work.

Intended evolution

Planned evolution areas include:

  • richer registry-aware prompt recipes;
  • section-level regeneration and protected-user-edit workflows;
  • stronger explainability and clarification loops;
  • improved package maturity with build, lint, typecheck, and release packaging parity.