The discussion centers on a project using AI and networked microphones to locate a mysterious beep, with users debating the practical efficiency of this high-tech approach versus simple manual methods like physical binary search or unpacking boxes. Participants also argue over whether the project represents genuine learning and utility or merely an unnecessary expenditure of computational resources for a trivial problem.
172 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4obra
superpowers
Shell2025–2026
obra / superpowers
superpowers
An agentic skills framework & software development methodology that works.
64Distinct people
77Mentions
3Explicit recommenders
316.7KGitHub stars
What to know before exploring
What it is
An agentic skills framework & software development methodology that works.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
https://github.com/obra/superpowers I use Opus/Sol with for /brainstorming, deepseek (on Pi) for /subagent-driven-development I love it, the docs are easily editable and when…
cthulberg used a recommendation phrase. 3 indexed comments match. This is a phrase match, not a verdict.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- gastownhall/beads · linked in 2 of the same discussions
- github/spec-kit · linked in 2 of the same discussions
- gsd-build/get-shit-done · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 11:19:25 AM UTC.
Mentions over time
HN mentions by month77 dated mentions
Observed mentions: 2025-10-11 14:41:58 UTC to 2026-09-26 02:10:10 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Oct 2025 | 2025-10-01 00:00:00 UTC | 2025-11-01 00:00:00 UTC | 6 | 1 | 5 |
| Nov 2025 | 2025-11-01 00:00:00 UTC | 2025-12-01 00:00:00 UTC | 3 | 0 | 3 |
| Dec 2025 | 2025-12-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 5 | 1 | 4 |
| Jan 2026 | 2026-01-01 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 7 | 2 | 5 |
| Feb 2026 | 2026-02-01 00:00:00 UTC | 2026-03-01 00:00:00 UTC | 10 | 2 | 8 |
| Mar 2026 | 2026-03-01 00:00:00 UTC | 2026-04-01 00:00:00 UTC | 9 | 3 | 6 |
| Apr 2026 | 2026-04-01 00:00:00 UTC | 2026-05-01 00:00:00 UTC | 12 | 3 | 9 |
| May 2026 | 2026-05-01 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 5 | 2 | 3 |
| Jun 2026 | 2026-06-01 00:00:00 UTC | 2026-07-01 00:00:00 UTC | 6 | 2 | 4 |
| Jul 2026 | 2026-07-01 00:00:00 UTC | 2026-08-01 00:00:00 UTC | 10 | 0 | 10 |
| Aug 2026 | 2026-08-01 00:00:00 UTC | 2026-09-01 00:00:00 UTC | 2 | 0 | 2 |
| Sep 2026 | 2026-09-01 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 2 | 0 | 2 |
What Hacker News says
9 sourcesSOsolidasparagus·Mar 28, 2026
I used them for repeated problems or workflows I encounter when running with the default. If I find myself needing to repeat myself about a certain thing a lot, I put it into claude.md. When that gets too big or I want to have detailed token-heavy instructions that are only occasionally needed, I create a skill.
I also import skills or groups of skills like Superpowers (https://github.com/obra/superpowers) when I want to try out someone else's approach to claude code for a while.
In Anatomy of the .claude/ folderShow HN: Arxitect – Claude Code plugin for software design principles
Show HN: Arxitect – Claude Code plugin for software design principles
Modern coding agents are getting exceptionally good at implementing a given coding task. And with validation-in-the-loop, you can be reasonably confident they will implement a correct solution. However, their implementation often leaves a lot to be desired. It doesn't adhere to the decades of software design best-practices that the community has established and is often myopic to broader software quality attributes like maintainability and extensibility. To make things worse, this low code quality compounds as coding agents implement additional tasks.
These design principles weren't established specifically to help humans...they were designed to make code easier to refactor, modify, extend, test, and maintain! And these properties matter just as much in an agentic world
Read the rest
. Design principles significantly reduce the amount of context humans or agents need to understand a codebase or implement a feature. They reduce the surface area for bugs, improve testing efficacy, and just generally make humans and agents more effective at building software.
This has been my biggest reservation for using coding agents on larger and more unstructured tasks, so I built Arxitect. I was inspired by the design of [Superpowers](https://github.com/obra/superpowers) and decided to extend that concept to software design principles.
Currently, it contains implementation and code review agents (and skills) that asses your code for:
*API Design - Assessing naming conventions, method signatures, parameter design, type safety, and REST endpoint design.
*Object Oriented Design - Assessing SOLID principles, DRY violations, composition vs. inheritance choices, and design pattern applicability.
*Clean Architecture - Assessing component cohesion, component coupling, and quality attributes like maintainability, extensibility, and testability.
Install in Claude Code with:
/plugin marketplace add andonimichael/arxitect
/plugin install arxitect@arxitect
/reload-plugins
I welcome any feedback, advice, or PRs at: https://github.com/andonimichael/arxitect
I've had a good experience with https://github.com/obra/superpowers. At first glance this looks similar. Has anyone tried both who can offer a comparison?
In Get Shit Done: A meta-prompting, context engineering and spec-driven dev systemthat reference you give is pretty dated now, based on a talk from August which is the Beforetimes of the newer models that have given such a step change in productivity.
The key change I've found is really around orchestration - as TFA says, you don't run the prompt yourself. The orchestrator runs the whole thing. It gets you to talk to the architect/planner, then the output of that plan is sent to another agent, automatically. In his case he's using an architect, a developer, and some reviewers. I've been using a Superpowers-based [0] orchestration system, which runs a brainstorm, then a design plan, then an implementation plan, then some devs, then some reviewers, and loops back to the implementation plan to check progress and correctness.
It's actually fun. I've been coding for 40+ years now, and I'm enjoying this :)
[0] https://github
Read the rest
Thanks! I assume you are referring to this https://github.com/obra/superpowers
I use it as well (a customized version suited for my worflow). It is indeed the GOAT.
In Show HN: Open-source browser for AI agentsSuperPowers: Agentic skills framework that works
4 points · Open discussionThe even more concerning news to me is that chardet 7.0 is now vibe coded AI slop, as documented in the PR for the rewrite [1]:
> I put this together using Claude Code with Opus 4.6 with the amazing https://github.com/obra/superpowers plugin in less than a week. It took a fair amount of iteration to get it dialed in quite like I wanted, but it took a project I had been putting off for many years and made it take ~4 days.
Given the amount of changes I seriously doubt that this re-implementation has been reviewed properly and I wonder how this is going to be maintainable going forward.
[1]: https://news.ycombinator.com/item?id=47259177
In No right to relicense this projecthttps://github.com/obra/superpowers "brainstorming" is pretty much exactly this workflow, and it's great.
In If AI writes code, should the session be part of the commit?