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-human-inquire

v0.1.1

Published

Human-in-the-loop document inquiry and feedback for Pi.

Downloads

307

Readme

pi-human-inquire

pi-human-inquire turns plans, notes, specs, RFCs, recaps, research, diffs, and other structured content into reviewable HTML where humans can ask agent questions and leave feedback directly inside the document.

It includes:

  • a human-review skill that creates reviewable HTML from structured content
  • a browser surface for comments, contextual questions, threaded discussion, and feedback submission

Install

Pi packages can be installed from git, npm, or a local path. Git is the recommended install path once the repo is published/renamed.

Try without installing

pi -e npm:pi-human-inquire

Install globally

pi install npm:pi-human-inquire

Install for a project

pi install -l npm:pi-human-inquire

Install from git

pi install git:github.com/alpeshvas/pi-human-inquire

Usage

Generate reviewable HTML from content

Use the skill:

/skill:human-review

You can invoke it with no arguments, with a file path, or with an instruction:

/skill:human-review notes.md
/skill:human-review turn this RFC into review HTML
/skill:human-review make the previous plan reviewable

The skill uses the provided content, or the most recent structured content in the conversation. It then creates an HTML file and opens it in the browser. If it cannot find suitable content, it asks you for a path or content.

Open existing HTML

If you already have an HTML file:

/annotate-html /absolute/path/to/document.html

Legacy alias:

/annotate-plan-html /absolute/path/to/document.html

Browser surface

In the opened HTML review page, you can:

  • click any block to ask agent questions or leave feedback
  • select text for comments
  • continue threaded agent Q&A in place
  • add document-level notes
  • edit or remove comments
  • submit feedback back into the active Pi session

Agent answers use the document, current block, selected text, existing comments, thread history, and recent session context.

Architecture

flowchart TD
  P["Pi package<br/>package.json"] --> S["Skill<br/>/skill:human-review"]
  P --> E["Extension<br/>commands + tool"]

  S --> H["Reviewable HTML"]
  S --> T["open_html_review"]
  E --> T
  E --> C["/annotate-html"]

  T --> B["Browser review page"]
  C --> B

  B --> BR["ctx.sessionManager.getBranch<br/>recent session context"]
  BR --> M["Active Pi model<br/>for threaded agent Q and A"]
  M --> B

  B --> F["pi.sendUserMessage<br/>deliverAs: followUp"]
  F --> PI["Active Pi session"]

Skill options

Use lite mode for quick/minimal output:

/skill:human-review --lite notes.md

Use stubs when iterating on a plan or spec and you want sections to remain stable across revisions:

/skill:human-review --with-stubs spec.md

By default, generated HTML is written to:

~/.agent/diagrams/<slug>.html

Feedback submission

Submitted feedback is saved locally and sent back into the active Pi session.

Compatibility notes

For now, /annotate-plan-html remains an alias for /annotate-html.