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

Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

github.com

Post reply on HN
Print view View original

251–260 of 278 posts

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#251

Post by j45 »

oakpond wrote: post #185
joegaebel wrote: post #146

In my view, Spec-Driven systems are doomed to fail. There's nothing that couples the english language specs you've written with the actual code and behaviour of the system - unless your agent is being insanely diligent and constantly checking if the entire system aligns with your specs. This has been solved already - automated testing. They encode behaviour of the system into executables which actually tell you if yo…

Sort of agreed. Natural language specs don't scale. They can't be used to accurately model and verify the behavior of complex systems. But they can be used as a guide to create formal language specs that can be used for that purpose. As long as the formal spec is considered to be the ground truth, I think it can scale. But yeah, that means some kind of code will be required.. :)

Things like Github's speckit seems to have a fair amount of usage.

The idea that specs are code now, is one can effectively rebuild in the future with newer models. Test requirements could be defined upfront in the specs too, no?

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#252

Post by canadiantim »

AndyNemmity wrote: post #126
canadiantim wrote: post #124

Earlier quoted context omitted.

That would be awesome. I believe with AI it's all about tailoring everything to your specific workflow and style, especially anything to do with the dev environment.

right, i'm having to cut out a lot of my pieces at the moment to try to get it into a release state. i have checks of which types of repos i'm in with branching dev flows for each one. it's going to be hard to communicate all of this genericly, but i am trying.

No worries if it's untenable or too much though, but I'll keep an eye on the commend thread in case!

For my part, I'm currently using oh-my-opencode harness with various skills extracted and tailored from superpowers / simonw / matt pocock. Working well enough so far, but keen to really evolve the skill flow and how they connect and are used in coordination with the various subagents.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#256

Post by nfg »

whalesalad wrote: post #202
nfg wrote: post #151

Earlier quoted context omitted.

As a matter of interest are you using the copilot cli?

yeah. copilot cli using opus 4.6 vs claude code using opus 4.6

If you could share I’d be really interested in hearing a concrete example of the two behaving differently. I work in Microsoft (not on copilot - though I’m an heavy user, and use Claude code in a personal capacity) and would be quite happy to repro and report back to the copilot cli team who are responsive.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#257

Post by AndyNemmity »

canadiantim wrote: post #252
AndyNemmity wrote: post #126

Earlier quoted context omitted.

right, i'm having to cut out a lot of my pieces at the moment to try to get it into a release state. i have checks of which types of repos i'm in with branching dev flows for each one. it's going to be hard to communicate all of this genericly, but i am trying.

No worries if it's untenable or too much though, but I'll keep an eye on the commend thread in case! For my part, I'm currently using oh-my-opencode harness with various skills extracted and tailored from superpowers / simonw / matt pocock. Working well enough so far, but keen to really evolve the skill flow and how they connect and are used in coordination with the various subagents.

I ended up releasing it. Let me know your thoughts

https://github.com/notque/claude-code-toolkit

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#258

Post by marcus_holmes »

auggierose wrote: post #178
marcus_holmes wrote: post #122

Earlier quoted context omitted.

I ended up grafting the brainstorm, design, and implementation planning skills from Superpowers onto a Ralph-based implementation layer that doesn't ask for my input once the implementation plan is complete. I have to run it in a Docker sandbox because of the dangerously set permissions but that is probably a good idea anyway. It's working, and I'm enjoying how productive it is, but it feels like a step on a journey…

If it is working, why is it just a step on a journey? What is missing?

It's a kludged-together dev process made up of two different systems in a docker container so potential damage is contained. It's not ideal ;)

Neither of those two systems feel evolved either. Superpowers is very cool, but there are holes still. And Ralph feels like an experiment that worked so they published it.

This is all going somewhere, evolving and moving towards some beautiful system. Or maybe the usual dev ecosystem shit - it'll be a great prototype and then it'll get overthought, overcomplicated and overengineered and end up less usable than what we had before *glares at React*

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#259

Post by marcus_holmes »

jghn wrote: post #197
marcus_holmes wrote: post #122

Earlier quoted context omitted.

I ended up grafting the brainstorm, design, and implementation planning skills from Superpowers onto a Ralph-based implementation layer that doesn't ask for my input once the implementation plan is complete. I have to run it in a Docker sandbox because of the dangerously set permissions but that is probably a good idea anyway. It's working, and I'm enjoying how productive it is, but it feels like a step on a journey…

did you hand modify the superpowers skills or are you managing this some other way?

yeah, I coped the skills I wanted into a directory, hacked away at them until they did what I wanted, and then added them to the dockerfile for the sandbox
Post reply on HN