> This entire codebase — Rust parsers, TypeScript renderers, tests, and tooling — is implemented by AI coding agents, primarily Claude and Codex, through iterative prompting. No human-written application code exists in this repository.
non one forces anyone to use something. just ignore and move on. The author had clearly stated that its 100% written by Claude and codex with proper prompting and spec document.
I'd love to see Codex adopt this for its Office file rendering. I've been working on a markdown-to-pptx tool lately, and certain things like tables or specific master slides don't quite render 100% accurate there. Missing table formatting or completely wrong font sizes. But they look 99% perfect here (I noticed one numbered list that didn't have enough whitespace between the number and the text).
It rendered a really long and complex documentation Word file perfectly though.
This project is super cool. And it shows what agent factories can do. However I’m not sure how well it’s protected against malicious tickets/actors.
Each time I found a bug. I (Claude code, let’s be real) post a detailed bug report. And this project usually fixes it in less than 24h.
So now, I have an agent pulling the newest changes each day checking if my issues is fixed.
It’s so much fun.
Btw: I have a very similar experience with the Mastra project.
This looks promising to me. I like the logo and the git commits definitely show they are crafting this. I wonder how can we identify ambitious, AI-assisted projects in a quick way.
13 comments
[ 0.23 ms ] story [ 6.4 ms ] thread> This entire codebase — Rust parsers, TypeScript renderers, tests, and tooling — is implemented by AI coding agents, primarily Claude and Codex, through iterative prompting. No human-written application code exists in this repository.
https://github.com/yukiyokotani/office-open-xml-viewer
I'd love to see Codex adopt this for its Office file rendering. I've been working on a markdown-to-pptx tool lately, and certain things like tables or specific master slides don't quite render 100% accurate there. Missing table formatting or completely wrong font sizes. But they look 99% perfect here (I noticed one numbered list that didn't have enough whitespace between the number and the text).
It rendered a really long and complex documentation Word file perfectly though.
Each time I found a bug. I (Claude code, let’s be real) post a detailed bug report. And this project usually fixes it in less than 24h. So now, I have an agent pulling the newest changes each day checking if my issues is fixed.
It’s so much fun.
Btw: I have a very similar experience with the Mastra project.
Edit: Oops, did not notice it was AI slop generated. They really need to add disclaimers on top of such projects. That's really bad.