Introducing /jamesian, a Claude skill that helps you de-homogenize LLM prose
Building bigger sentences for a better world
OK, after a flurry of revisions, I have a Claude skill based on the “de-LLMifier” I built last night. You can find it here, and the video below shows how to install it and use it. It’s super simple:
I built to use on LLM prose, but you can use it for human prose as well, to think about your own ideas for revising a sentence (though as the irreplaceable John Warner notes in a comment below, that use has less of a clear utility).
A lot of the extension is the addition of presets. So if you take this LLM produced prose on Invasion of the Body Snatchers, which is perfectly fine but also sounds like all other ChatGPT prose, you can now ask it for different levels of structural complexity.
Original
The 1956 film is often interpreted as an allegory for Cold War paranoia, particularly the fear of communism infiltrating American society. Its central theme revolves around the loss of individuality through conformity, but it presents this threat in a relatively straightforward moral framework: the “enemy” is external and identifiable. In contrast, the 1978 version deepens this theme by making the loss of identity more ambiguous and internalized. Rather than simply fearing an outside force, the remake suggests that people may already be emotionally disconnected, making them susceptible to replacement without resistance.
Baroque (“highest” setting)
The 1956 film is often read as Cold War allegory, a parable of communist infiltration in which the enemy, external and nameable, burrows into ordinary American life under cover of the familiar: the neighbor, the small-town doctor. Its theme is the loss of individuality through conformity. Where the 1956 film externalizes its threat, the 1978 remake relocates it inward, into a zone where identity leaks away without any clear enemy to resist. The remake suggests something darker than mere invasion: that people may already be emotionally disconnected, already hollowed out by the ambient conditions of late-1970s urban life, susceptible to replacement because so little remains in them worth the effort of resistance.
Now, going up in complexity (sorry, had to show the most dramatic comparison first).
Tight (very short sentences)
The 1956 film is often read as Cold War allegory, its pod people cast as communist infiltrators. Its theme is the loss of individuality through conformity. The moral frame is clear: the enemy is external. The 1978 remake internalizes the threat. Identity loss becomes ambiguous and intimate. People may already be emotionally disconnected, susceptible to replacement without resistance.
Balanced
The 1956 film is often read as Cold War allegory, its pod people cast as communist infiltrators. Its theme is the loss of individuality through conformity. The moral frame is clear. The enemy is external and identifiable. Where the 1956 film externalizes its threat, the 1978 remake internalizes it. Identity loss becomes ambiguous and interior. People may already be emotionally disconnected, susceptible to replacement without resistance.
Layered
The 1956 film is often read as Cold War allegory, a parable of communist infiltration in which the enemy is external and identifiable, locatable once you know what to look for. Its theme is the loss of individuality through conformity. Where the 1956 film externalizes its threat, locating the enemy in pods and infiltrators, the 1978 remake relocates the threat inward, into zones of feeling the characters no longer fully inhabit. The remake suggests something darker. People may already be emotionally disconnected, susceptible to replacement because so little remains in them worth defending.
Expansive
Read since its release as Cold War allegory, especially a parable of communist infiltration, the 1956 film locates the threat outside the self. Its central theme is the loss of individuality through conformity. The moral frame is relatively clear, the enemy external and identifiable. The 1978 remake deepens the theme by relocating it, moving the loss of identity inward, where it becomes ambiguous and close to the bone. The remake suggests something darker: that people may already be emotionally disconnected, already susceptible to replacement without resistance.
Baroque
The 1956 film is often read as Cold War allegory, a parable of communist infiltration in which the enemy, external and nameable, burrows into ordinary American life under cover of the familiar: the neighbor, the small-town doctor. Its theme is the loss of individuality through conformity. Where the 1956 film externalizes its threat, the 1978 remake relocates it inward, into a zone where identity leaks away without any clear enemy to resist. The remake suggests something darker than mere invasion: that people may already be emotionally disconnected, already hollowed out by the ambient conditions of late-1970s urban life, susceptible to replacement because so little remains in them worth the effort of resistance.
Revision of human prose
I initially wrote this to solve a problem with LLM prose. As I crafted the prompt and tested it, I did think more and more about what use it might have to someone looking to figure out a problem they are having with their own writing. In this mode I don’t think of it as an automatic paragraph generator, but as something that might open a stuck writer’s eyes to a range of possibilities they hadn’t seen, which they could then take in places and reintegrate into their work.
I’m not sure it would be helpful to long-time writers. I’ve been writing blog posts for twenty years, and my style is fairly automatic at this point, and pretty developed. Technology is likely to get in the way. But for people still learning prose rhythm and sentence structures, it might be beneficial? If you teach a composition class and think it could have a use let me know, and if you do use it and its a disaster let me know that too. In this particular area I have no real sense of its worth, I just think it might be interesting to see if students find any value in it. Do they engage with it and finally get a sense of the infinite variety of writing one can produce from a small set of facts? Or does it become just one more site of cognitive surrender?

This is fun! I find it interesting to see the different styles, and how the same themes can be reworked into different sentence shapes and orderings in the paragraph. I teach undergrad and graduate courses in Composition. For the same reasons John Warner cites, I would avoid this in undergraduate classes--except the ones I teach themed on AI. :)
But I think it would be interesting in grad classes, or those focused on style. I could imagine students feeding in an LLM or Wikipedia paragraph, running it through your Jamesian stylizer, then observing and annotating all of the versions: what makes it baroque? What's actually happening to these sentences and vocabulary? In which styles are you more likely to see dependent clauses? etc. Then have them work through their own prose following some of the patterns they gleaned from your stylizer: rewrite using at least three dependent clauses; make 4 of your words into Latinate versions; then do the reverse by using only sentences under 10 words each, etc. etc. That would be, I think, a productive style exercise that would help students get those "reps" that John recommends.
It's very clever. I liked John Warner's discussion on style vs. voice. I think the former is easier to "program" while the latter takes years of practice and writing and feedback and response to hone. I've also been blogging for over 20 years - and it's authenticity that appeals to people (I hope) in some contexts whereas if you're just writing reports or "call and response" type texts I guess it doesn't really matter.
What seems to work with middle schoolers (my domain) is slower nudges - e.g. through chat bots so that they're still doing the work and refining and redrafting. I'm very nervous of the current phenomenon of the first draft being the only draft. Which has always been a student inclination but when education was slower one could insist on several (handwritten) drafts.
I'm wondering if seeing your own physical work change and improve viscerally is a different thing than seeing digital magic.
We gain some and we lose some.