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

pi-inquisitor

v0.3.0

Published

Interactive form tool for pi — radio and checkbox questions with AI-powered elaboration

Readme

pi-inquisitor

Interactive form tool for pi. Ask the user structured questions with radio buttons and checkboxes — with inline AI elaboration.

Why

LLMs ask users questions constantly — which framework, what database, deploy where. Plain-text questions produce sloppy answers: typos, ambiguity, the LLM guessing what "the second one" means. pi-inquisitor gives the LLM one tool (ask_user) that presents structured forms and returns clean, machine-readable results.

Install

pi install npm:pi-inquisitor

Or try it without installing:

pi -e npm:pi-inquisitor

How it works

The LLM calls ask_user with a list of questions. Each question is either radio (single-select) or checkbox (multi-select) with predefined options. The user picks from the options in an interactive TUI form and the result goes back to the LLM as plain text.

Tool

{
  "title": "Database choice",
  "questions": [
    {
      "id": "db",
      "type": "radio",
      "prompt": "Which database?",
      "options": [
        { "value": "postgres", "label": "PostgreSQL", "recommended": true },
        { "value": "sqlite", "label": "SQLite" },
        { "value": "mongo", "label": "MongoDB" }
      ]
    }
  ]
}

Question types

| Type | Description | |------|-------------| | radio | Single-select. Enter picks the focused option. | | checkbox | Multi-select. Space toggles, Enter advances. |

Every question gets an "Other..." option by default (allowOther: true) so the user can type a custom answer. Options support description (help text) and recommended (badge).

Elaborate

Press E on any option to stream a terse AI-generated analysis inline:

Pros: <one sentence>
Cons: <one sentence>
Best when: <one sentence>

Uses the session's system prompt and full conversation history for context. One-shot per option, 15-second timeout.

Navigation

| Key | Action | |-----|--------| | ↑/↓ | Navigate options | | Tab / Shift+Tab, ←/→ | Switch questions (multi-question forms) | | Space | Toggle checkbox / select radio | | Enter | Select and advance (radio) / advance (checkbox) / submit (final tab) | | A | Select all / deselect all (checkboxes) | | E | Elaborate on focused option | | Esc | Cancel form |