I've just used this extensively to build 200 Shortcuts for my event-based automation app on macOS [0], because some actions you simply can't do without Shortcuts: changing Focus Mode, toggling Accessibility functions like Color Filters, accessing the Private Cloud Compute model etc.
I also wrote about how Claude was able to basically learn the language from scratch and write those fully compilable Shortcuts for me [1] because it was mind boggling to me that an LLM can do that. Curiously, this is becoming more and more normal in my mind.
Looks quite cool and I'd like to give a try. What is the main use case for compiling code to shortcuts? I ask because I'm working on a tool[0] that in a way does the opposite.
I’m interested to understand how this is different than Jelly; they seem to be similar. Same for Scriptable. I’ve been looking at this to hand over to Claude to build Shortcuts, something which has a terrible development experience.
From the repo, it signs natively on macOS and falls back to a cloud signing server (shortcut-signing-server). That fallback matters -- without macOS you would have to reverse-engineer Apple signing format yourself, and it changes across iOS versions. The hosted signing server is really what makes the whole cross-platform toolchain viable.
I also wrote about how Claude was able to basically learn the language from scratch and write those fully compilable Shortcuts for me [1] because it was mind boggling to me that an LLM can do that. Curiously, this is becoming more and more normal in my mind.
[0] https://lowtechguys.com/crank
[1] https://alinpanaitiu.com/blog/how-good-is-claude-really/#che...
[0] https://breadboards.io
(That's what held me back most for spending more effort on shortcuts.)