Isn't this mainly a skill injected in the context? Rather a model/platform specific feature?

Lovely you discovered devcontainers.

Ollama is quite a bad example here. Despite popular, it's a simple wrapper and more and more pushed by the app it wraps llama.cpp.

Don't understand here the parallel.

TBVH I didn't think about naming it too much. I defaulted to Ollama because of the perceive simplicity and I wanted that same perceived simplicity to help adoption.

This is the vLLM of classic ML, not Ollama.

I guess the parallel is "Ollama serve" which provides you with a direct REST API to interact with a LLM.

llama-cpp provides an API server as well via llama-server (and a competent webgui too).

You can improve a lot the success rate with providing HELM and clear instructions with the tool description.

Over a year ago had a lot of issues and the description and example was the difference between 30-50% failure to 1%!

So I'm surprised a bit about the point. May be I'm missing it.

Why in nushell? Not in go?

But I like the idea and principle. OSS need this and it's traded very lightly.

Mitchell has really enjoyed Nu essentially. If it is implemented in a shell script, it probably also means that general shell tooling can work with the format.

Devcontainer is not docker and do the trick!

How to do agentic workflow like 2 years ago.

What would SOA be?

Claude Code is perfectly able to access your git/jj history directly. Just ask it to review a commit.

Claims as always misleading as they don't show the context length or prefill if you use a lot of context. As it will be fun waiting minutes for a reply.

Issue llama.cpp is shipped and no more updated. Or you need to download it all.

This is killing me with complexity. We had agents.md and were supposed to augment the context there. Now back to cursor rules and another md file to ingest.

MCPs feel complicated. Skills seem to me like the simplest possible design for a mechanism for adding extra capabilities to an existing coding agent.

Can skills completely replace MCPs? For example, can a skill be configured to launch my local Python program in its own venv. I don’t want Claude to spend time spinning up a runtime

Skills only work if you have a code environment up and running and available for a coding agent to execute commands in.

You can absolutely have a skill that tells the coding agent how to use Python with your preferred virtual environment mechanism.

I ended up solving that in a slightly different way - I have a Claude hook that spits attempts to run "python" or "python3" and returns an error saying "use uv run instead".

I tell Claude to make its own skills. “Which part of this task is worth making a skill for, use your skill making skill to do it”

If we aren’t in the take off phase, I don’t know where we are

Skills are just pointers to context so you don't need to load all of them upfront, it is as simple as that. By the way cursor rules is effectively the same as agents.md.