I’m interested in how this works in practise - I guess you’ve written a skill to do code review, then your Claude.md file tells it to use it after every change as a bg task? So does this work as a background task while Claude is working on the next ‘feature’?
There are many "critics", one for each quality I want reviewed. Correctness, consistency, maintainability, security, testing... Everything I could think of, and I keep adding more.
The scrutinize skill is the entry point. The Opus I'm talking to becomes an agent coordinator. He explores and autodiscovers the project's structure, subdivides it into logical sections.
Then he runs a truly absurd critic x section matrix against the entire project. Literally hundreds of these agents running in parallel, each focusing on one area. Ten minutes of this is enough to exhaust my Max 5x five hour window and put a serious dent in the weekly usage numbers.
It literally takes days to run a full agent sweep. I designed it around the rate limiting. The agents do file system style journaling in order to resume cleanly. They commit all of their findings as they go into an orphan branch in the repository. Further review runs can build on it and avoid searching for known issues.
The way it works in practice is I just run /scrutinize sweep and then go work on something else, or just go do my actual job, live my life, play video games, write an article for my blog or something. Come back five hours later to either resume the process or check the literally hundreds of issues that have been found by all the agents. Then Claude and myself will go in and evaluate and fix all of those issues one by one. Then review again. Then evaluate/fix again. I'm just gonna keep looping this over and over until zero issues are found. For all of my projects.
Going from solo hobbyist programmer to this was pretty insane. I can only imagine what these corporations with infinite money must be doing.
Those critic skills are great. I see a real business opportunity for someone who can bundle everything you describe into a turnkey solution for a programmer like me who doesn't want to take months coming up with their own system and extensive .md files.
I'm currently, very painfully, removing a tiny bit of tech debt at a time from a massively complex project that we inherited from a 3rd-party vendor. Some of the tech debt is AI-related, some because it's a vendor who rarely has to maintain anything they create, some because when we first inherited it we had no grasp on the entire codebase and were just trying to change the plane wheels while flying (we still are).
What I'm doing now is the hardest kind of programming imo. I spend hours/week just meditating on how to chip away at this out-of-control codebase, figuring out how I can surgically remove some leaky abstraction that's spawned 5 cousins w/o disrupting the whole project. I'd be fascinated to see if the latest frontier model with a system like yours can actually help me. But I don't have the time or desire to invest the months of trial and error that I'm sure it took you to get to that point.
I used Claude Code's /insights function. It gets Claude himself to go over your sessions and usage patterns. It'll produce an HTML report that you can view.
In my case Claude saw that code review was my main activity and that I was manually and repeatedly asking claude to "review X, Y, Z..." so he suggested turning it into a skill. So I fired up the superpowers:brainstorming skill and bikeshedded it until I ended up with this heavy duty massively parallel super reviewing super claude. Refined it a bit after a couple weeks of use and the result is what you see in my repository.
You're welcome. Email me when you discover your own path? I could learn a thing or two as well. I'm pretty much a beginner when it comes to this stuff. Subscribed like two months ago.
I would advise against it, depending on the project.
My lone lisp project gets the most love. I spend weeks reading, reviewing, restructuring and rewriting everything. It's the project where I'm concentrating all my efforts. Everything I push to master is absolutely my own work and I do want everyone to read it.
I had no trouble letting Claude take over maintenance of my static site generator and virtual machine orchestration scripts though. I wanted to care but... I didn't. I did glance over the finished product just to ensure it wasn't going to nuke my laptop the second it ran, but that's pretty much the extent of it.
It’s also a very western view - block printing was a thing in China well before this. I don’t know, but I suspect there are older surviving presses there or in Asia more generally.
“These results are not applicable to typical buildings, where outdoor-to-indoor air exchange already removes volatile organic compounds (VOCs) at a rate that could only be matched by the placement of 10–1000 plants/m2 of a building's floor space.[2]
The results also failed to replicate in future studies”
I also agree co2 levels are super important, but I’m wondering: in your situation isn’t air pollution from the motorway a concern? Not sure how to balance that one
I am probably one of the few people here that used this ‘in anger’. Around 15 years ago I would typeset orders of service in tex for our college chapel, and enjoyed typesetting the chant - this tool made it really easy and I could produce IMO beautiful documents.
Most of the time people used bitmaps which would be blurred/pixelated or not resize well
You can…but, won’t the frequency will be stable across the UK grid and these are all in London. Secondly, pretty sure they all use DC motors, so no hum
When reading "Books of the Century" I expected a list of the most important, most influential or just best books. Skewed towards the french perspective, given Le Monde as a source. But this was never the goal, just a "what stuck in your mind" question.
For example, 1984 is missing, and Louis Begley Wartime Lies. And I wouldn't have expected Ulysses in there given the french source, for me it was incomprehensible gibberish and I thought only the US ranks it high. But that gibberishness makes it certainly memorable, so given the question it fits.
Ulysses was written in Paris, where James Joyce lived, and was published in Paris by the now legendary Shakespeare & Co. The US and UK banned it for being obscene.
When I don't know, I ask and don't judge (and lacking omniscience, I don't judge anyway).
It's completely irrelevant where it was written, where it was published and where it was banned, I'm talking about how it is seen today. It is possible I am getting this wrong -certainly possible, since I'm taking this impression from English speaking sites like this, that I attribute to the US what should be attributed to England -, but I have seen no argument so far that even strives the point I made.
What is your question? If you just want to know why Ulysses is seen as influential you can start with the wikipedia article. If you want to try again to read it you can try to read it with a guide of some kind, there are multiple, I used this one https://www.ulyssesguide.com/1-telemachus.
No question. It's completely against my being to consider something as good if it can't be enjoyed without a guide. I hated the tendency in computer science to hide simple definitions behind jargon. I'm okay with stuff having hidden meaning, with texts being interpretable, I'm not okay with it just being gibberish when not studying it in closest detail.
I'm aware that some think this book is influential, I'm not clear on how widespread that belief is. Also, whether regular readers really like it. And no, Wikipedia does not clear that up.
Of course it's relevant to how it's seen today. French culture nurtured the author, a French publisher published it, and France didn't ban it while other countries did. This is all evidence that the book was well-liked in France when it was published, and there's no reason to think that would change over time.
If anything, it's surprising that English-speaking countries like it so much.
I disagree, those aren't relevant factors. Just based on those facts it's possible there was one sponsor in France who published the book and then it bombed, never to be read by a significant amount of the public. That it wasn't banned is normal in a free society, but also says nothing about its popularity.
Ulysses was first published in Paris during the 20 years that Joyce lived there.
>I thought only the US ranks it high
Joyce never even set foot in the United States... You could say this about The Great Gatsby, which US sources might rank in the top 5 compared to 46 in this list.
Right, Great Gatsby is another book one could highlight, where it's surprising that it is on the (french) list, while it would be on an US list. But I haven't read it, I do not know whether it is a good example for the difference between a good or important book and a memorable one.
If you found Ulysses confusing, what would you think of Finnegan's Wake? Ulysses is practically a children's book in comparison. As for the lack of 1984, Orwell was an important author sure, but not particularly a good one. People read 1984 and Animal Farm for the messages, not for the exquisite prose that someone like Joyce can manage.
Sorry, I haven't tried to read that one. If it's even more, hm, abstract?, then I won't ever try.
Note that 1984 is listed, just as "Nineteen Eighty-Four". I missed it when searching, didn't think of searching for "Orwell" instead.
I'd disagree with you about its quality, I remember it fondly (well, as much as possible given the topic of having one's identity erased), it was a powerful experience - and I do remember it vividly, so when asked for books one remembers I'd absolutely mention it, and in a list of books of the century it does belong.
Joyce "prose" on the other hand did nothing for me but make me despise his book.
James Joyce wearing his bottle bottom glasses (thick glasses) would like to have a word with you. You can call him genius, dirty, knowledgeable in many languages but certainly not gibberish. He used to hold long book club style readings of his books among the prominent literateur in his times to exactly impinge in their minds that what he writes is clever and not gibberish. In our book club we often discuss for hours what he was trying to say on a page. Sometimes he says things in 3 different dimensions by writing a single sentence.
> He used to hold long book club style readings of his books among the prominent literateur in his times to exactly impinge in their minds that what he writes is clever and not gibberish.
My was so clever, that he had to verbally harangue people into finding his writing clever.
Starting with only 200 titles in the survey, for a final list of 100, seems off to me for starters. Every book surveyed has a 50% chance of making “book of the century”
Obviously 50/50 if random. But even if not random, I estimate 50 Shades would be 500-100,000 times more likely to be a book of the century using a list of 200 with it in it, vs an unaided open ended survey.
Here, pets have always had to be identifiable: historically with a collar, but microchips have been required for some years now as a more effective method.
reply