osr00

/i-have-adhd or /the-writing-whip are also pretty good as well with Opus 5!

I still use Opus 4.6 and 4.8 regularly, as I often find Opus 5 too verbose (and Fable too expensive). You can add them back to the /model picker using the "modelPicker" array in settings.json

Better late than never... Now it's time for Claude Code to load skills from .agents/skills!

I used Authelia in the past, I'm curious: why not using Cloudflare Access?

Many of the apps I ended up not using was either because the projects were abandoned or because the web/app UX is just too bad or ugly. For instance I really like Photoprism but Immich has such a better app experience imo.

I recently discovered Arpeggi (client for my Navidrome server) and I have such a good time using it

> How do you find skills

I try to keep my collection of community skills short, usually a few established names (mattpocock, mcollina, trailsofbit). And then I check new releases (or when mattpocock published a youtube video for instance :D)

> keep them organized

For skills I wrote myself, I have my own private github repo. I use skills like /commands most of the time, so I can tell if they work straight away.

For community skills, a package manager really helps. vercel-labs/skills and withastro/rosie are good options. I also built one myself: https://github.com/osrim/ski. It has some cool features like an update command and a security scan.

Seems too easy :D I can see how this gets you up and running with a twin env on a simple stack, I have more questions about the enterprise setup: I couldn't find much on cloud services, does it emulate AWS services like s3/SQS?

"you probably shouldn’t let it write it for you if you actually expect the rest of us to read it." definitely resonates with me.

Where I kind of disagree is that I don't think most readers will revolt. I think the mountain of LLM slop has actually changed people's behavior in more ways than one. Some are already relying on LLMs to summarize articles: then it doesn't matter to them who wrote it, they're just consuming machine-condensed content with no way to tell if a human or an LLM wrote the original piece. Or if their summarizer hallucinated.