You can ask Claude to "sdoc me an annotated code walkthrough of this MR" and it will produce something like this:

https://smalldocs.org/s/Ju9GOmWZ0JXTtzqCVfgt1q#k=6HBrpcCjIu7...

I use this a lot to stay in touch with the code the LLM is producing.

[1] https://smalldocs.org [2] https://github.com/espressoplease/smalldocs

Can you easily share lists or pages or is it all local? (Is there a cloud element to it)

What are the most useful examples you’ve personally found when it comes to using the HYML component?

I built https://smalldocs.org for my agent’s Markdown needs. I extended it so it can render complex formats: Mermaid diagrams, charts, in-document slides and even in-document spreadsheets. It gives your agent a good selection of formats to express itself as it helps you understand whatever topic you’re looking into.

Here is a sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

I publish anonymous analytics here: https://smalldocs.org/analytics

https://smalldocs.org/s/2SH6FHiUK1mcym24Z8E37I#k=2Sk6c_IdKJL...

[1] I am the developer behind SmallDocs.

Given my experience building this, I think the idea of "a truly independent document":

> one that displays identically on any system, in any country, for any user, regardless of the software used

Will be very difficult to achieve in practice.

Building software is an expression of opinions. And one of the main drivers of building an app is to innovate or improve the user experience vs. what exists today. These things combine to result in new features, and new features breaks the open standard.

If I wanted to build a new Excel, I might want to add something to spreadsheets which a basic open source reader cannot, or even Excel itself, might not be able to handle.

With SmallDocs, I built on the standard rendering of markdown, but then added a bunch of properties which traditional markdown renders would ignore.

For example, styles front matter:

  ---
  styles:
    fontFamily: Lora
    baseFontSize: 17
    h1: { fontSize: 2.3, fontWeight: 700 }
    p: { lineHeight: 1.9, marginBottom: 1.2 }
    ...
  ---

And slide blocks like:

  ~~~slide
  grid 100 56.25 bg=#0b1220
  r 6 9 82 4 text=caption color=#fbbf24 align=left | LAUNCH   REVIEW  -  Q2 2026
  r 6 18 84 16 text=title color=#f8fafc align=left | Atlas 2.0 shipped to every customer
  r 6 37 78 6 text=subtitle color=#94a3b8 align=left | What changed, what it cost, and what we learned
  l 6 47 24 47 stroke=#fbbf24 strokeWidth=0.2
  ~~~

All this means SmallDocs markdown files only render correctly through our rendering engine - but this enables me to add something new to an existing document format.

[1] https://smalldocs.com; https://github.com/espressoplease/smalldocs

Claude can right great code, but it’ll throw comments into the code about why we chose this approach instead of the random one I discussed with it - when the comment is of no use to a future developer.

It points at some sort of theory of mind problem in LLMs imo.

They can do a lot of cool things! Mermaid gallery here: https://smalldocs.org/s/xZrc-lNW1kbXpoIuU3l_ky#k=-0ehGe2B-hR...

I’ve been building https://smalldocs.org for this exact reason. It’s an office suite for AI agents - but my main use case is giving a cli based LLM the canvas to express itself - charts, mermaid diagrams, etc. I’ve extended it a bit further to be a format for all types of work so the agent can embed slides and spreadsheets in a document.

Sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

Source: https://github.com/espressoplease/smalldocs

Here is the mermaid diagram gallery: https://smalldocs.org/s/PpArByXuNBA5kGS1JVMUW6#k=uTqNRLqzz_T...

Code available: https://github.com/espressoplease/smalldocs

Discord: https://discord.gg/txjATTsDaq

I say it’s as if “Claude Code & Microsoft Office had a baby...”

Code available: https://github.com/espressoplease/smalldocs

Discord: https://discord.gg/txjATTsDaq

Sample document: https://smalldocs.org/blogs/what-is-a-smalldoc

Invoked via Claude Code by saying stuff like: “sdoc me the plan for this feature”, or “dig into our logs and sdoc me a report on our latency"