Show HN: /show-me: agent skill for compact visual representations

(humanlayer.com)

12 points | by dhorthy a day ago ago

3 comments

  • bhkdotdev a day ago ago

    This is really great! I have a few personal skills I've been maintaining for generating and rendering mermaid diagrams but the overall coverage here is way beyond what I was doing. ++ to visuals being a key missing tool in a lot of these harnesses.

    Not sure how you're testing the output of this but I posted about my tool i've been working on earlier today https://news.ycombinator.com/item?id=49274758 and spun up a quick (very basic) test suite example for this:

    https://github.com/dynobox/examples/blob/main/.agents/skills...

  • janpeuker 9 hours ago ago

    For all of my love for open weight models, them being not fully multi-modal or just plain bad at visual understanding like this is my major reasons for not using them more

    • dhorthy 6 hours ago ago

      they seem to be able to do the call-stack diff stuff pretty well still