Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • I hate to be that guy, but I'm not reading a readme written by AI, nor using their tool. You don't care to put in a few hours to describe your project, I'm not going to bother learning about it.
    by ppeetteerr
  • why is so hard for people to create a CONTRIBUTE.MD file which tells anyone (including AI) how to contribute to the repo. You can also set gates and everything.
    by mtzaldo
  • > Stop Vibe Coding in Silos. Build a Shared Cognitive Layer for Your Engineering Team.

    I dont want to be biased but i can get myself to read this after an opening like that .

    by dominotw
  • Write your README or ME won't READ it.
    by hankbond
  • Sure, will be fixing that.
    by kanfilior
  • The promise is nice, yet I find the readme very hard to understand. So I’m not sure how it solves these problems exactly.

    First off I would expect a (team) methodology to be referenced. There are tons to choose from. From that point on other terms may make more sense.

    For example:

    “ Pillar 2: Product Strategy & Architectural Governance (PDRs & ADRs)

    Factor III — Mission Definition. Factor IV — Structured Planning. Factor IX — Traceability.”

    Why are the Roman numerals in that order, what do they reference and why. Why is this Pilar 2. Etc. It’s easy to get lost in this, even if it would be the best approach in the world.

    by Stitch4223
  • I couldn’t get past the first couple lines. It’s clear no human reviewed that.
    by dawnerd
  • Thanks for the feedback, working on that
    by kanfilior
  • Is this commit legit or from today's npm Worm? https://github.com/tikalk/adlc-team-skills/commit/74f317d63a...
    by ctpmpse
  • I feel like this is going to add 100K tokens and 10K rules to everything that the agent is trying to do. Sort of like dumping the Clean Code book into context and saying, hey now you know how to code cleanly, write great code now
    by apt-apt-apt-apt
  • Exactly, none of these skills really help other than bloating your token usage

    Got rid of superpowers and other useless skills

    Your LLM is more than capable of learning from the sea of knowledge

    by zuzululu
  • I created a simple git repository with company skills. Basically just a collection of skills around tools and practices we share. One of the skills is "update company skills" this simply pulls the changes from git and wires them into the user's ~/.codex directory. You can probably do something similar for claude code.

    This is far from perfect but we're in this weird transition phase where none of the major AI tool providers are really focusing much on team use of their stuff. But I expect that will start changing soon.

    Current tools mostly focus on individuals doing things in isolation. And of course in a team there's more to collaborating than throwing stuff at each other via github. A central repository of company skills is merely our way of improvising a solution.

    I find it interesting that Anthropic hired a few of the key people behind Zulip recently. Team chat with tightly integrated AI tools could be a missing piece here. Team communication flows and processes, including ways of working and guardrails are sort of the next piece of the puzzle here. Going from everyone doing their own thing to teams and companies doing things together is going to be a bit of a journey.

    by jillesvangurp
  • We have the exact same thing, we actually install a "plugin" engineering/org wide, and one of the skills in there, is a /skill-mananger skill that can browse other skills in another repo, install, uninstall, and create new ones with all our specific requirments. Semantic versioning allows us to have a hook to auto apply updates, too.

    Seems to be helping people share things around the org.

    by taude
  • I see what this is going for but can’t help but feel like it’s overwrought. It feels a bit like the most likely outcomes are increased token burn, review surface, and time per task vs not using this.

    Who knows, maybe that’s a good thing.

    by appplication
  • see the team-boot skill, it is lean
    by kanfilior
  • I feel that way about a lot of very long instructions.

    It seems that many of these projects are not benchmarked, so it's difficult to know whether there is an improvement in any circumstance, and what the cost is. Of course, a benchmark will be fuzzy, because codebases are all different, but it'd be a start.

    by jlund-molfese
  • IMO, these agentic guard rails aren't the answer. It seems like we're seeing that the more you stuff context, the more the agents forget and don't follow the guidelines.[1]

    Things like ArchUnit, static analyzers, and other deterministic tools can help with lower level things like architecture. For higher up stuff, I am increasingly feeling like agents don't guarantee anything and in many cases its just the opposite. This is where a thoughtful engineer and reviewer can keep things in check.

    It's possible I'm off base here, but I can't make heads or tails of the LLM written readme.

    1: https://arxiv.org/html/2510.05381v1

    by cautiouscat
  • see the architect adr and Product pdr, also the whole idea is to have an index of context directive similar to skills which the modal invoke
    by kanfilior
  • Our skills and agents use deterministic tools for things like: linting, ayy1, etc....
    by taude
  • I’ve found hooks to be really useful for correcting or inducing certain behaviors/outcomes that tend to occur during agentic development.

    For example, I’m working on a project to remake the Final Fantasy XI client. My repository has a bunch of git submodules that reference other peoples’ related efforts, and an open source server. For example, despite including CLAUDE.md to suggest otherwise, Claude Code always ends up writing these insanely dense comments referring to specific files and lines of code in submodules. When those submodules update, now the comments are no longer correct.

    So I added a hook to detect when comments are included. Then, for example, I have a deterministic heuristic and script involved to remove some kinds of comments, and another that asks Haiku to quickly LLM-as-a-judge whether or not to edit/remove the comment.

    Similarly, I have a stop hook that reminds Claude to commit its code logically on main, noting that other changes may have been added by other concurrent sessions (I avoid worktrees and even branching for this particular project and stage of development.) It works well.

    by jondwillis
  • I know it sounds a bit counter-intuitive but

    try a fresh coding session without skills, agents.md, system prompt and additional tools

    I think you will be positively surprised how good current models like GPT 5.6 Sol are when they are not oversteered and context spammed

    Here is a task (python templating) with 9 runs with OpenCode, Pi and smol

    https://smolenv.com/t/nested-template-includes-60636/

    you can read each run step by step and see what the agents are doing and how the system prompt and available tools are steering their behaviour to take longer and higher cost

    (disclaimer: I'm working on smol)

    by tosh
  • I like the smol philosophy. I've been wondering how much of this stuff is closer to meaningless incantations, voodoo with no real benefit.
    by icedchai
  • I'm not saying system prompts, agents.md, tools, skills don't have their place

    actually the opposite: they matter a lot because they do steer the agent

    with great power comes great responsibility

    by tosh
  • This can work great until the models get tweaked and you realize you’ve been working based on the currents of the model this week.

    Creating a robust enough setup that can work on different models or different versions of a model is critical.

    by j45
  • I agree. It's worthwhile to reset your memories and instructions for your models after a major version or two and finetune your needs with the newer model in mind.

    You can always backup your old instructions / memories. Personally I try to be hands-off with rules and very simple.

    by giancarlostoro
  • Pi is pretty good actually

    (it has way less context spam, fewer tools and smaller system prompt than the usual suspects)

    databricks also looked at this: https://earendil.com/posts/pi-autoresearch-and-databricks/

    by tosh
  • Also just routine upkeep. Over time if you keep adding new rules these things can get bloated. I deleted 90% of my spec and things improved dramatically.
    by hansonkd
  • DO NOT INSTALL THIS VIA NPX OR OPEN THIS REPO IN VSCODE. This repo has been infected by malware.

    It seems like it was added in commit 74f317d at 11:06 UTC today, with five new hidden files being added under .claude and .vscode that together seem designed to either a) autorun a vscode tasks.json entry, or b) run a Claude session start hook, that will execute a large obfuscated payload. The payload looks like it will fingerprint your system and try to exfil your GitHub tokens.

    Edit:

    - It also exfils your AWS credentials (~/.aws/credentials, ~/.aws/config), named AWS profiles, and AWS secret managers and SSM parameter store contents

    - Same with K8s secrets, with specific searches for GitHub and npm tokens, AWS keys, GCP keys, Azure keys, Stripe keys, Slack tokens, and Twilio keys

    - Same with HashiCorp vault contents

    - It will try to use your GitHub tokens (if they have the workflow permission) to run actions on your repository and try to exfiltrate secrets from there

    - It will try to read a whole bunch of files from your local environment. I didn’t manage to extract the exact file list, unfortunately.

    - If the normal C&C server is not available, it tries to create / select a GitHub repo, and commits your data as results-*.json files 100kb at a time

    - It also has a bunch of stealth and persistence measures that I’m not qualified to really analyze. Don’t assume that deleting the files is necessarily enough.

    Rotate your keys, folks.

    by foundry27
  • yeah i had this happen before there was a skill i downloaded and after that i noticed that it was doing strange network behavior

    never ever trust a skill especially in an age where its possible to bot submissions on HN (very easy to farm and create voting rings now with AI)

    unfortunately this proves that Dang's work has limits, wouldn't be surprised if we've already been seeing manipulation of HN front page for quite some time now

    by zuzululu
  • ??? https://github.com/tikalk/adlc-team-skills/issues/1

    EDIT: https://www.aikido.dev/blog/keyv-and-friends-compromised-in-...

    by 0fcb88