There have been a few similar posts on HN recently for working with MS Office docs:

https://github.com/iOfficeAI/OfficeCLI

https://github.com/rcarmo/python-office-mcp-server

https://github.com/espressoplease/smalldocs

It would be great to see some benchmarks for token use, correctness, features etc.

fair point! i've got some stats in the body of the github, and a skill that has the eval that i've built for it.

A "standing review agent" seems to be one of the main differences beyond the new connectors and in place visualisation tools.

>A standing reviewer agent. This runs in the background during a session, checking citations against sources, flagging numbers it can't trace back to evidence, and catching figures that don't match the code that supposedly generated them. That's not something Code or Cowork do automatically — you'd have to ask Claude to double-check itself as a separate step.

I had the same experience with a prompt about an antibody's structure and properties.

A few implementations listed on LM Studio. Any recommendations for which one to use?

Yes, very questionable. They also missed New Zealand which is the largest exporter of dairy products (~ 21%).

Nature Food is one of those also ran journals that sully the brand. None of my colleagues in related fields bother with it.

The Netherlands is almost legendary for its agricultural productivity. Its greenhouse operations were the model for NZ capsicum production and other efforts. It also leads food science research in some areas. Wageningen is perhaps the best in that field.

"The 60 Minute Zoom" is a good short story to start with.

Will this convert websites into RSS feeds? Can I run a daily update on them?

Interesting video on the history of Worcestershire Sauce (fermented anchovy base):

https://www.youtube.com/watch?v=0q5QhGnEKUM

Addendum: https://www.youtube.com/watch?v=RvF2m57_Usg