29 comments

  • Planktonne 1 hour ago
    This is cruft [1]. No one who is capable of using this needs it--it's a line in the prompt at most.

    [1] https://knowyourmeme.com/memes/thinking-quickly-dave-constru...

    • rspeele 11 minutes ago
      I have yet to see an "agent skill" that does not match this description.
      • hedgehog 6 minutes ago
        They are useful for packaging all the related bits together. Some instructions on the line to add to the main prompt, detailed policy doc that spells out details, troubleshooting docs, the code itself, etc.
    • alansaber 53 minutes ago
  • dan_sbl 1 hour ago
    I took one of the examples ("Leveraging sqlpipe's robust...") and just prefixed it with this:

    > Rewrite this using ASD-STE100 simplified technical English:

    And you get a good-enough result, it seems? Maybe add another sentence or two for guidance, but what's with needing these giant skills, when ASD-STE100 was surely in the training material?

  • boardwaalk 4 minutes ago
    the problem I’ve found with these things is that models drift immediately. if it’s not a git commit hook that runs over docs and comments and commit messages objectively it’s probably useless. which I might try.

    Claude is so friggin wordy and has no idea how place comments iff they actually matter.

  • tajd 1 hour ago
    On a related note I wrote a skill to apply the economist style guide to LLM generated writing https://github.com/TAJD/economist-style-guide-plugin

    Tends to produce relatively well structured prose that’s easy to edit.

  • hsaliak 30 minutes ago
    Seems to be doing too much, a 1 line in the system prompt is all you need. And it works well enough.

    “Output tokens are precious, be succinct in your responses. Use ASD-STE100 simplified technical english”

  • abeyer 45 minutes ago
    STE Misapplication issues and limited adoption

    https://en.wikipedia.org/wiki/Simplified_Technical_English#M...

  • dawnerd 5 minutes ago
    TIL There's a spec for how I normally communicate instructions at work.
  • bayesnet 2 hours ago
    It’s ironic that the README has all the tells of being LLM-written: > 53 numbered rules, 9 sections, written in 1983 by people whose readers die when a sentence is ambiguous. The ones doing the heavy lifting: …

    Not really a promising tell for a writing skill, IMO.

    • mcintyre1994 1 hour ago
      They acknowledge this, but I really dislike whatever style they're using for the readme:

      > Yes, this README breaks half of them. Marketing is explicitly out of STE scope. The skill knows that and stays in the docs.

      > Where it refuses to go: marketing copy, blog voice, brand writing. Flat on purpose.

      (Each sentence there has an emoji that HN cuts out)

      • bcrosby95 8 minutes ago
        The problem with at least ChatGPT is no matter what personality you set it still reads like a smug asshole trying really hard to sound smart. You can just pick different flavors of smug asshole.
    • gchamonlive 1 hour ago
      The readme looks to me concise and correct. Tested it and it works. Better than many human-written readmes I've seen around.
  • summarity 45 minutes ago
    Gotta love how the very first example in Issue 9 of the standard is already self-defeating:

    > "Test" is an approved noun, but not an approved verb.

    > STE: Test B is an alternative to test A.

    So much for clear - unless you know the STE specific rule, the sentence is unambiguously ambiguous.

    Direct access btw since the official site gates downloads with a Google form: https://www.asd-ste100.org/assets/files/ASD-STE100_ISSUE9.pd...

  • dylan9n 11 minutes ago
    Didnt use it on the readme for the repo
  • gillesjacobs 33 minutes ago
    https://youtu.be/uJblcC4lKYw

    This video benchmarks slop-style indicators with different skill/prompt solutions including the STE skill vs. George Orwell's six rules of writing prompt: Orwell came out on top overall.

    Additional bonus: it doesn't add much more tokens to input context. I have compared prose prompts with these rules and without and I am liking the results.

      1. Never use a metaphor, simile, or other figure of speech which you are used to seeing in print.
      2. Never use a long word where a short one will do.
      3. If it is possible to cut a word out, always cut it out.
      4. Never use the passive where you can use the active.
      5. Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.
      6. Break any of these rules sooner than say anything outright barbarous.
  • jpease 1 hour ago
    I like the idea, but not sold on the skill.

    But did lead to me finding https://vale.sh and its various available linters. Might give that a try.

  • hankbond 2 hours ago
    ["Skill", "Force"]

    Pick one.

    • CGMthrowaway 2 hours ago
      Here is the revised post title that follows ASD‑STE100 Simplified Technical English rules:

      "Agent Skill to Enforce ASD-STE100 Simplified Technical English in Documents"

  • alehlopeh 1 hour ago
    No semicolons — write two sentences.

    Oh lord.

  • alansaber 54 minutes ago
    The irony of vibing a de-sloppinator
  • handfuloflight 3 hours ago
    Okay here's one of the outputs:

    > Before you start, make sure that your AWS credentials are correct. If they are not, S3 rejects the upload with a permission error.

    Wouldn't it be better to write:

    Before start, ensure AWS credentials are correct. Otherwise, S3 rejects uploads with permission error.

    • harshreality 2 hours ago
      The example is unambiguous. Your modification is ambiguous at best. <failure to ensure aws credentials are correct> != <aws credentials are incorrect>
    • qznc 1 hour ago
      Violates rule 4.2: Do not omit words or use contractions to shorten sentences. Keep articles, keep "that".
    • stavros 2 hours ago
      No, how is that better?
    • trhway 2 hours ago
      Which one would do better in a college essay? I think the original one, and it has higher word count.
  • SoMomentary 1 hour ago
    Anyone tried this as an output style and not just as a skill?
    • nevi-me 1 hour ago
      I've added the prompt to use the ASD English, on my CLAUDE.md when I learnt of the standard. The generated output is more tolerable to read, and is less confusing.

      I like it, and I'll also try the Economist one on another thread here. I have global instructions on how Claude should try to write things like I do.

      I generally avoid having lots of skills, security risk as I won't vet them all.

  • cesarvarela 1 hour ago
    Man, I was just now imploring Claude to be more concise.
  • codingjoe 2 hours ago
    What a wonderful skill. I hate the long and verbose do strings or docs LLMs spit out. This will make a great addition to my docu agent.

    And I agree, maybe I should use this for my emails too

  • z3ugma 1 hour ago
    Also from a nicely explained YouTube video: https://www.youtube.com/watch?v=uJblcC4lKYw " The cure for AI slop is a 1986 aircraft manual"

    https://github.com/woosal1337/blog/tree/main/videos/ep01-the...

  • grim_io 1 hour ago
    I wish this were selectable as the default output style.
  • cryo32 1 hour ago
    The day I have to negotiate and persuade the machine to stop talking shit rather than command it is the day I decide fuck it and go and farm geese or something.

    Smells like today. I’ll take goose shit over this.

  • ricardobeat 1 hour ago
    The very first sections of the README having obvious claude-isms is not very reassuring:

    > AI slop dies as a side effect

    > One folder, no dependencies, MIT.

  • evanjrowley 3 hours ago
    Honestly I should use this on my own emails and slack messages.
  • bbg2401 3 hours ago
    Oh, is ASD-STE100 this week’s mindless productivity/AI-bro trend?

    Ads-STE100: Simplified Technical English - https://news.ycombinator.com/item?id=49101215

    ASD-STE100 Simplified Technical English for LLMs - https://news.ycombinator.com/item?id=49065956

    ASD-STE100 Simplified Technical English [pdf] - https://news.ycombinator.com/item?id=49075687

    Show HN: Claude Skill for ASD-STE100 – Simplified English - https://news.ycombinator.com/item?id=49108318

    • xlii 2 hours ago
      New models (especially Opus 5, released just last week) produces unintelligible output, so people are trying to fix it.
    • gck1 54 minutes ago
      Recent-ish models learned to use the same trick engineers played on non-engineers, where they try to sound very smart by overcomplicating very simple concepts.

      It's very taxing, especially since these are usually multi-paragraph texts. I noticed I've started doing a lot of "hey, you're talking gibberish again" a lot with 5.6 Sol.

    • UqWBcuFx6NV4r 2 hours ago
      What’s it like to be this abrasive about people simply doing things?
      • bbg2401 1 hour ago
        It would be nice if people were indeed doing things.

        However, asking Claude to write a skill encoding ASD-STE100 after seeing it pop-up in your social feed is not doing much at all. It's certainly not worth a post on HN.

        Having said that, this skill might have been the seed for the flurry of low-effort posts on the subject on various platforms this week. If that's the case, I take back the majority of my scorn.

        You'll have to excuse me for becoming jaded by the diminishing levels of visible effort put into projects and products shared on here.

        • mastodon_acc 37 minutes ago
          Not everyone spends their time browsing hackernews or other forums all day.

          This is the first time I’m hearing about this, I think it’s nifty, and it’s precisely why I come to hackernews at least once a day.

          Also what is wrong with using Claude to make a more polished post about something that’s being talked about already?

          • wonnage 29 minutes ago
            This is actually completely useless slop and any illusion of usefulness is misguided
    • tonyarkles 2 hours ago
      You didn’t link to it but I looked back at my very few submissions and realized that I had posted it in 2019. I thought it sounded familiar!
    • toomuchtodo 1 hour ago
  • alikhater30000 12 minutes ago
    [flagged]
  • dahdum 2 hours ago
    [dead]
  • nikolahristov 2 hours ago
    [dead]
  • Merkur 3 hours ago
    nice :-) i'll try that! thx