> be github
> invent copilot
> you are literally the first one
> you are literally the only one
> you literally have access to all the code in the world
> get mogged by literally every single agentic bs that came out in the past few years
this level of fumble should be studied
if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt
Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!
The ~1M Convex projects are running on a cluster of ~1000 nodes that assign timestamps etc. There's also a large cluster that runs transactions plus a big sharded PlanetScale cluster underneath.
We use Nomad for cluster management, which we find more ergonomic than Kubernetes.
I see a lot of complaints about untested AI slop in pull requests. Submitting those is a dereliction of duty as a software engineer: Your job is to deliver code you have proven to work https://t.co/Eso7BWaTtF
The ty test suite is "written" in Markdown. Every code block here gets evaluated, with the comments representing expectations.
We have almost 300 of these files that effectively read as detailed documentation for how ty behaves and how the Python typing spec and runtime work.