Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Superpowers: How I'm using coding agents in October 2025

blog.fsck.com

Post reply on HN
Print view View original

41–50 of 242 posts

Re: Superpowers: How I'm using coding agents in October 2025

#41

Post by spankibalt »

Avicebron wrote: post #7

I often feel these types of blogposts would be more helpful if they demonstrated someone using the tools to build something non-trivial. Is Claude really "learning new skills" when you feed it a book, or does it present it like that because you're prompting encourages that sort of response-behavior. I feel like it has to demo Claude with the new skills and Claude without. Maybe I'm a curmudgeon but most of these type…

> "Maybe I'm a curmudgeon but most of these types of blogs feel like marketing pieces with the important bit is that so much is left unsaid and not shown, that it comes off like a kid trying to hype up their own work without the benefit of nuance or depth."

C'mon, such self-congratulatory "Look at My Potency: How I'm using Nicknack.exe" fluffies always were and always will be a staple of the IT industry.

Re: Superpowers: How I'm using coding agents in October 2025

#42

Post by therealdrag0 »

jmull wrote: post #15

> …*RIGHT NOW, go read… I don’t like the looks of that. If I used this, how soon before those instructions would be in conflict with my actual priorities? Not everything can be the first law.

Seems like maintaining a bashrc file. Sometimes you have to go tweak it.

Re: Superpowers: How I'm using coding agents in October 2025

#44

Post by intended »

This isnt science, or engineering.

This is voodoo.

It likely works - but knowing that YAGNI is a thing, means at some level you are invoking a cultural touchstone for a very specific group of humans.

Edit -

I dug into the superpowers and skills for a bit. Definitely learned from it.

There’s stuff that doesn’t make sense to me on a conceptual basis. For example in the skill to preserve productive tensions. There’s a part that goes :

> The trade-off is real and won't disappear with clever engineering

There’s no dimension for “valid” or prediction for tradeoff.

I can guess that if the preceding context already outlines tradeoffs clearly, or somehow encodes that there is no clever solution that threads the needle - then this section can work.

Just imagining what dimensions must be encoding some of this suggests that it’s … it won’t work for situations where the example wasn’t already encoded in the training. (Not sure how to phrase it)

Re: Superpowers: How I'm using coding agents in October 2025

#45

Post by j_bum »

simonw wrote: post #31
Avicebron wrote: post #7

I often feel these types of blogposts would be more helpful if they demonstrated someone using the tools to build something non-trivial. Is Claude really "learning new skills" when you feed it a book, or does it present it like that because you're prompting encourages that sort of response-behavior. I feel like it has to demo Claude with the new skills and Claude without. Maybe I'm a curmudgeon but most of these type…

Here's one from today: https://mitchellh.com/writing/non-trivial-vibing

This was a fun read.

I’ve similarly been using spec.md and running to-do.md files that capture detailed descriptions of the problems and their scoped history. I mark each of my to-do’s with informational tags: [BUG], [FEAT], etc.

I point the LLM to the exact to-do (or section of to-do’s) with the spec.md in memory and let it work.

This has been working very well for me.

Re: Superpowers: How I'm using coding agents in October 2025

#46

Post by simonw »

apwell23 wrote: post #40

[flagged]

Here's a counter-example for you from the another day: https://simonwillison.net/2025/Oct/8/claude-datasette-plugin...

> This isn’t necessarily surprising, but it’s worth noting anyway. Claude Sonnet 4.5 is capable of building a full Datasette plugin now.

I do worry a bit about how often I use positive adjectives. If something isn't notable I won't write about it though. In this particle case Jesse's prompting / skills stuff really does deserve the superlatives IMO.

Re: Superpowers: How I'm using coding agents in October 2025

#47

Post by apwell23 »

simonw wrote: post #46
apwell23 wrote: post #40

[flagged]

Here's a counter-example for you from the another day: https://simonwillison.net/2025/Oct/8/claude-datasette-plugin... > This isn’t necessarily surprising, but it’s worth noting anyway. Claude Sonnet 4.5 is capable of building a full Datasette plugin now. I do worry a bit about how often I use positive adjectives. If something isn't notable I won't write about it though. In this particle case Jesse's prompting / skil…

well explain why OPost is "wild" and what makes you recommend it "strongly" .

what have u built with to come to those conclusions ? is this too much to ask.

Re: Superpowers: How I'm using coding agents in October 2025

#48

Post by simonw »

daemontus wrote: post #28

Maybe this is a naive question, but how are "skills" different from just adding a bunch od examples of good/bad behavior into the prompt? As far as I can tell, each skill file is a bunch of good/bad examples of something. Is the difference that the model chooses when to load a certain skill into context?

I think that's one of the key things: skills don't take up any of the model context until the model actively seeks out and uses them.

Jesse on Bluesky: https://bsky.app/profile/s.ly/post/3m2srmkergc2p

> The core of it is VERY token light. It pulls in one doc of fewer than 2k tokens. As it needs bits of the process, it runs a shell script to search for them. The long end to end chat for the planning and implementation process for that todo list app was 100k tokens.

> It uses subagents to manage token-heavy stuff, including all the actual implementation.

Re: Superpowers: How I'm using coding agents in October 2025

#49

Post by echelon »

cynicalsecurity wrote: post #35

Superpower: AI slop.

I'm sure the horse whip manufacturers had similar things to say about steam powered horses. We just don't think about them much anymore.

The whole world is changing around us and nothing is secure. I would not gamble that the market for our engineering careers is safe with so much disruption happening.

Tools like Lovable are going to put lots of pressure on technical web designers.

Business processes may conform to the new shape and channels for information delivery, causing more consolidation and less duplication.

Or perhaps the barrier to entry for new engineers, in a worldwide marketplace, lowers dramatically. We have accessible new tools to teach, new tools to translate, new tools to coordinate...

And that's just the bear case where nothing improves from what we have today.

Re: Superpowers: How I'm using coding agents in October 2025

#50

Post by evanmoran »

spprashant wrote: post #26

I am not ashamed to admit this whole agentic coding movement has moved beyond me. Not only do I have know everything about the code, data and domain, but now I need to understand this whole AI system which is a meta skill of its own. I fear I may never be able catch up till someone comes along and simplifies it for pleb consumption.

To give you a process that might help:

I’ve found you have to use Claude Code to do something small. And as you do it iterate on the CLAUDE.md input prompt to refine what it does by default. As it doesn't do it your way, change it to see if you can fix how it works. The agent is then equivalent to calling chatgpt / sonnet 1000 times a hour. So these refinements (skills in the post are a meta approach) are all about how to tune the workflow to be more accurate for your project and fit your mental model. So as you tune the md file you’ll start to feel what is possible and understand agent capabilities much better.

So short story you have to try it, but long story its the iteration of the meta prompt approach that teaches you whats possible.

Post reply on HN