Claude Code knows a lot about programming in general, but very little about the tools and conventions we use every day. Skills close that gap. A skill is nothing more than a Markdown file with instructions that Claude loads when it needs it. Let us see how we can add a few useful ones to our setup, and how we keep that setup from growing out of control.
Last week we configured Findle so that we can have a local search and fetch solution that is based on Docker. In this post we see how we can connect our AI tools to Findle and use it to search the web.
One thing I noticed with GSD Pi was that it took ages to find the right methods to build the applications I had in my Image Locator exercise . This was mainly because I did not add an online search service like Brave or Tavily to keep all the data on the test machines. But what would be if we run such a search gateway on our local machine? Let us find out how that could work.
Last week we noticed an annoying behaviour in Claude Code that could have cost us a lot if we did not catch it in time. Keep always in mind that an AI coding agent is as so many other LLMs trained to agree with the user. However, that is often not what we want, especially when we try to come up with new ways to do things and ask for a review. Let us see what happened and how we pushed back.
In last week’s post we connected two NVIDIA DGX Sparks . With this connection in place, we can now continue and run vLLM on our two-machine cluster to access the 256GB RAM of both machines.
The NVIDIA DGX Spark comes in many variations, like the Dell Pro Max with GB10 or the HP ZGX Nano AI Station . They vary in the case, but inside we have basically the same GB10 board with the same AI capabilities. The integrated 128GB RAM is great, but for mid-sized models more RAM would be helpful. Luckily for us, we can connect multiple DGX Sparks together and increase the model size we can…
When we run LM Studio on a NVIDIA GB 10, we cannot use the graphical user interface. But there is the helpful lms command that allows us to do all the configuration in the command line. Let us see how we can work with this tool.
It is already two months since I covered GSD and Superpowers that give a more structured development approach to Claude Code. In the meantime, GSD released a fully autonomous application called GSD2 that works outside of Claude Code but still uses their infrastructure. With the new pricing model this kind of application is not covered by the monthly subscription and requires API pricing. Let us…
In the first part we saw how easy it is to connect Claude Code to a local LLM and in the second part we measured the performance we can get with various local models . In this final part we explore the code we created while measuring the performance aspects.
In the first part last week we saw what we need to run Claude Code with a local LLM. In this second part we take a closer look at the different models and how they perform on different machines. Then the 'right' model does not help us much if we cannot run it with the needed context size or when it only produces a few tokens per second. This is the hard part of running Claude Code against a local…
Running Claude Code against a self-hosted LLM is much simpler than I expected. All we need are environment variables and the local LLM itself and we are good to go. However, that is just the start, and the challenges arrive when we try to do some real work. Let us see what we can do to tackle those challenges.
Creating the first CLAUDE.md file is not much work as we saw in last week's post . However, getting an initial file and something that helps us is not necessarily the same. Why not use Claude to improve our CLAUDE.md file?
As we saw in the insights report from last week , there are usually a few suggestions on how to improve our CLAUDE.md file. But if you never used a CLAUDE.md file that may not help you enough. In this post we take a close look at this helpful file and how we can use it to our advantage.
Claude Code gave us in April a new feature that allows us to see how we use Claude Code. Even better, it is not only a tool to show us what we did, but it helps us to get better. Let us see how it works.
If you return to Claude Code after a few weeks of vacation, you may be way behind on all the new things that you now can do with Claude Code. Let us explore a few ways to get up to date and not to miss important updates.
When we use tools like GSD , Claude Code does a ton of work for us. It does it so fast, that we cannot keep track. Did it call a specific tool? What was our input? If those are questions you would like an answer for, then this post is for you.
After a rather disappointing experience with OpenSpec I kept looking further and found Superpowers and Get Shit Done (GSD) as candidates for another round of tests. I tried to build the same application as with OpenSpec and found some interesting differences.
OpenSpec brings spec-driven development (SDD) to AI coding assistants. The idea is that we move away from vibe coding and use well-established practices for software development inside our AI coding tools. While I love the idea, my first experience was not that promising. Let us see what happened.
AI coding agents are impressive. Give them a prompt, and they can scaffold apps, write tests, refactor code, and even debug tricky issues. That speed makes them feel almost magical. But anyone who has used them on a real project learns the same lesson quickly: the quality of the output depends heavily on the quality of the requirements. Requirements are not bureaucratic overhead. They are the map…
When we use AI coding tools we have to be careful that we do not fall into the prototype trap. Then just because we can prompt a prototype in a few hours does not mean we can take a few additional sessions and turn it into an application. Let us see what I mean by that.