Superpowers 6

<- Back

Superpowers 6

seahorseemoji

Comments (68)

losvedir
Superpowers feels like 20 years ago when people would be sharing and debating their incredibly elaborate .vimrc files, which totally made them super productive. Meanwhile, I tried to stick to stock configuration as much as possible (mostly for portability / ssh reasons). In a similar vein, these days some of my colleagues are sharing all their skills and prompt tricks and stuff, and I try to just use barebones Claude Code as much as possible, and I feel like it keeps getting better and better and all these prompt shenanigans are just not worth it.
tmach32
I used Superpowers for a few weeks. I ran into a couple issues:* I wish I could turn it on selectively. Many of my requests do not require the "verification before completion" and TDD ceremony. For example, agents using stock Superpowers will go so far as to grep a file every time you ask to add something to them to verify that the edit really landed.* While I like speccing out/designing a project before implementation (nothing new in that regard), I don't like how precisely superpowers plans out the implementation in the /writing-plans skill. It tells future agents exactly what files to edit. There are two big issues with this: * We need to manage context rot. If one LLM session is responsible for writing out the entire plan, we aren't solving context rot. Not only is the "smart window" of context exhausted by the time the agent is planning, eg, step 7 out of 15, but it's also dragging forward all the possibly bad ideas it had earlier. It would be better if steps were planned independently. * Implementation is an iterative process. You find things out as you go. Your assumptions turned out to be wrong, you realize APIs don't behave the way you thought you did, etc. This is why writing out a precise plan ahead of time is an issue – it's written without this iteration. IMO, the strongest part of Superpowers is /subagent-driven-development. Yes, it's SUPER slow. For a laugh, you can ask it to make a change you know can be done in one line. It'll do it in one line, but it take literally an hour with all the verification. But that's sort of the point. It is _very_ deliberate. For each step, it reviews the step for both compliance and code quality, then has another agent implement the fixes, _and then it reviews the fixes again_. It does this for every step (not at the end of the project). While this might seem like overkill, it leads to code which complies with the spec far better.Instead of writing a super detailed spec, I think I'd like /writing-plans to come up with appropriate "units" of work (sometimes called slices) and to brainstorm with the user regarding implementation, but to leave it looser than "edit this exact file in this exact way". That should leave a lot more leeway to implementation agents but still give the review agents something to check compliance against.
prplfsh
For what it's worth, I really enjoy superpowers. In particular, it does a great job with TDD that stops the model from jumping to conclusions, and I've been able to get it, even with Opus, to execute on much longer specs quite well.
dmix
Neither the article or the corporate blog post explains what Superpowers is. Seems to be an opinionated collection of skills for dev workhttps://github.com/obra/superpowers
smusamashah
Where I $work, someone used Superpowers to pull off two big projects that before AI have always been left untouched because of the effort and time required. One was about unifying lots of duplicating (but kot exactly) libraries, and another to convert our bespoke shell scripts used throughout deployment pipeline to ansible.When I used it though , I only found it burning too many tokens to do too little. I guess Superpowers is useful only in hands that know how to manipulate it.
Amekedl
The screenshot of ol' claude closed code with that ascii table tells it all: Vapor AIware.As if it really would work like that. The noise added by the verbosity alone is not taken care of enough, and this entire thing belongs on the great pile of ai vaporware.
YuukiRey
I can't believe that a bunch of Markdown files now comes with a "Commercial Services" section. It feels like an elaborate GitHub Karma farm. Everything has to be commercialized and advertised.
overflowy
How does Superpowers compare with Matt Pocock's skills[1]? I only tried the latter, and to be honest, I had positive results without burning a quadrillion tokens.[1] https://www.youtube.com/watch?v=-QFHIoCo-Ko
artisin
I gave Superpowers 5.x a whirl for a week, and aside from consuming a stupid amount of tokens, it did materially worse across all my personal benchmarks and general day-to-day development compared to plain Codex/Claude. I'm convinced it's either some 4D ploy by the AI cartels to set tokens ablaze, or it only provides Superpowers to those without any power to begin with. Rating: 1/5 Pinocchios. Would not recommend.
mcintyre1994
I think I’ve mostly found superpowers helpful, especially for TDD. It’s cool from this blog (and their GitHub) that they’ve verified it in various ways too. One issue is that I’ll sometimes see it wanting to write a whole doc for a follow on feature with a similar structure and have to tell it to just use the last one again.The most annoying thing is that it always pauses before implementing to ask if I want it to use Subagents (which it always recommends) or not.
jadbox
How do I know if this is worthwhile without any benchmarks against 'not using Superpowers'?
linsomniac
My use case is I have them installed and let Claude decide when to use them. Looks like for my recent sessions it has been using superpowers:test-driven-development 5%, and superpowers:subagent-driven... 1%. I haven't really been working on new projects this past week though which seems to be where they fire off the most, in particular the "writing a plan" one.
ra
The cool thing about superpowers is it's built using evals rather than just vibes.
michelb
I’m a big fan of the Compound Engineering plugin from Every. As an amateur developer it helps me brainstorm, plan and implement apps very well.https://github.com/everyinc/compound-engineering-plugin
byzantinegene
seems like this would perform better with cheap open-source models on OpenCode compared to proprietary models like Claude Code or Codex.
RomanPushkin
Superpowers is pretty much convincing LLMs they can do better. It almost never works that way.
mortsnort
Anyone have an opinion comparing this to GSD?
SoMomentary
I've loved Superpowers right along. I think a lot of what it does has been ingested into Claude Code proper now so I'll be interested to see if this release actually changes things up.
anon
undefined
devnonymous
I'm honestly surprised at all the people here commenting that superpowers didn't work out for them.For me personally, it was a game changer when I first began using it and now it simply is as much a part of my workflow as any say, using git (yeah it has its warts but way way more value).Also, the latest (version 6) is noticebly token efficient as claimed.Did the people who found it underwhelming not try starting with the brainstorming skill first?
cyanydeez
i just dont find skills work flow all that generic enough.
mempko
This is great in concept but what prevents me from using it is TDD. I don't want to waste tokens on producing code that doesn't ship to the end user. Design by Contract is a far superior approach. If you've never heard of Design by Contract I don't blame you, our culture really failed to bring it mainstream. But I swear by it and it gives me real superpowers. Maybe I should fork this and gut the TDD part and replace it.
AIorNot
All these prompt and skill based git repos are sus... nothing is benchmarked -its all so subjective and unproven and breaks with model updates -everyone and his uncle has a 'secret sauce skill' -that just proves to me the subjectivity of this endeavor.
johnfn
To be blunt I can't take this product seriously when they don't even run benchmarks. Your prompts make Claude better? Cool: prove it. Methods to evaluate LLM performance exist, they're called evals/benchmarks, and every company that is serious about AI runs them when they release a new version. (Of course benchmarks have their own issues, but squabbling over which benchmark is best and what issues there are is step 2 in being a Serious AI Company and step 1 is running them at all!) The fact that the only proof they have that 6 is better than five is a hacky table in a screenshot from Fable is, honestly, concerning.
rahimnathwani
I thought this would be about https://github.com/obra/superpowers