# gsd (blogs) — RSS Amplifier Recent posts from the 2 feeds in the RSS Amplifier directory that cover gsd. Page: Feed: --- ## [Create Your Own Skills for Claude Code](https://ImproveAndRepeat.com/2026/08/create-your-own-skills-for-claude-code/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-08-18 · Improve & Repeat_ Last week we installed skills that other people wrote. The more interesting ones are the skills nobody else can write for us, because they encode how our team works. Anthropic ships a plugin for exactly that job, and its most valuable part is not the writing but the measuring. Let us see how this works. ## [Get More Out of Claude Code With Skills](https://ImproveAndRepeat.com/2026/08/get-more-out-of-claude-code-with-skills/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-08-11 · Improve & Repeat_ 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. ## [How to Use Findle in LM Studio, Claude Code & GSD Pi](https://ImproveAndRepeat.com/2026/08/how-to-use-findle-in-lm-studio-claude-code-gsd-pi/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-08-04 · Improve & Repeat_ 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. ## [Scott Spark RC by Dangerholm](https://www.bikehugger.com/posts/scott-spark-rc-by-dangerholm/) _2026-08-02 · Byron · Bike Hugger_ Scott Spark RC by Dangerholm: The Ultimate XC Flex Dangerholm is back with another Spark RC masterpiece—this time built around Scott’s 5th‑generation frame. That’s a… The post Scott Spark RC by Dangerholm appeared first on Bike Hugger . ## [Cargo Bikes vs Cars Impact](https://www.bikehugger.com/posts/cargo-bikes-vs-cars-impact/) _2026-07-31 · Byron · Bike Hugger_ Cargo Bikes vs. Cars: New Research Shows Cargo Bike Sharing Really Does Change Behavior Cargo bikes have been having a moment — from family hauling… The post Cargo Bikes vs Cars Impact appeared first on Bike Hugger . ## [Findle - A Local MCP Server to Find Things](https://ImproveAndRepeat.com/2026/07/findle-a-local-mcp-server-to-find-things/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-07-28 · Improve & Repeat_ 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. ## [When Claude Code Lies to You](https://ImproveAndRepeat.com/2026/07/when-claude-code-lies-to-you/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-07-21 · Improve & Repeat_ 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. ## [Tern’s New HSD Levels Up Cargo Biking](https://www.bikehugger.com/posts/terns-new-hsd-levels-up-cargo-biking/) _2026-07-15 · Byron · Bike Hugger_ Tern’s New HSD Levels Up Cargo Biking Without Upsizing the Bike Tern has refreshed its compact cargo platform with an all-new HSD that stays short… The post Tern’s New HSD Levels Up Cargo Biking appeared first on Bike Hugger . ## [How to Run vLLM on Two NVIDIA DGX Sparks](https://ImproveAndRepeat.com/2026/07/how-to-run-vllm-on-two-nvidia-dgx-sparks/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-07-14 · Improve & Repeat_ 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. ## [Story of the Tern GSD](https://www.bikehugger.com/posts/story-of-the-tern-gsd/) _2026-07-08 · Byron · Bike Hugger_ The Story of the Tern GSD was shared today by Fully Charged in an upload to their YouTube channel. The Tern GSD didn’t invent the… The post Story of the Tern GSD appeared first on Bike Hugger . ## [CLI-first decentralized GPU compute (Sponsored)](https://crawlproof.com/a/J8aAe9zZzvkI) _2026-07-08 · **Sponsored**_ Pay workers or run your GPU for FFmpeg transcode and AI inference. ## [How to Connect Two NVIDIA DGX Sparks](https://ImproveAndRepeat.com/2026/07/how-to-connect-two-nvidia-dgx-sparks/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-07-07 · Improve & Repeat_ 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… ## [Helpful Commands for LM Studio's CLI Tool](https://ImproveAndRepeat.com/2026/06/helpful-commands-for-lm-studios-cli-tool/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-06-30 · Improve & Repeat_ 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. ## [How to Run GSD PI With a Local LLM](https://ImproveAndRepeat.com/2026/06/how-to-run-gsd-pi-with-a-local-llm/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-06-23 · Improve & Repeat_ 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… ## [How to Run Claude Code With a Local LLM (3/3)](https://ImproveAndRepeat.com/2026/06/how-to-run-claude-code-with-a-local-llm-part-3/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-06-16 · Improve & Repeat_ 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. ## [Bike Hugger at 20 Years](https://www.bikehugger.com/posts/bike-hugger-at-20-years/) _2026-06-10 · Byron · Bike Hugger_ Bike Hugger at 20 Years There’s so much happening at once that I might’ve blown right past this milestone if not for a routine WordPress… The post Bike Hugger at 20 Years appeared first on Bike Hugger . ## [How to Run Claude Code With a Local LLM (2/3)](https://ImproveAndRepeat.com/2026/06/how-to-run-claude-code-with-a-local-llm-part-2/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-06-09 · Improve & Repeat_ 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… ## [Tern Orox Technology Shines](https://www.bikehugger.com/posts/tern-orox-technology-shines/) _2026-06-03 · Byron · Bike Hugger_ Tern Orox Technology Shines with the Bosch Flow App It turns out the Tern Orox into something more than an eBike. The Tern Orox is… The post Tern Orox Technology Shines appeared first on Bike Hugger . ## [How to Run Claude Code With a Local LLM (1/3)](https://ImproveAndRepeat.com/2026/06/how-to-run-claude-code-with-a-local-llm-part-1/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-06-02 · Improve & Repeat_ 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. ## [Use Claude to Improve the CLAUDE.md File](https://ImproveAndRepeat.com/2026/05/use-claude-to-improve-the-claudemd-file/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-05-26 · Improve & Repeat_ 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? ## [Stop Repeating Yourself: Put Project Context in CLAUDE.md](https://ImproveAndRepeat.com/2026/05/stop-repeating-yourself-put-project-context-in-claudemd/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-05-19 · Improve & Repeat_ 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. ## [Chovy's Blog: Agentic Coding (Sponsored)](https://crawlproof.com/a/5LpHavPG7yWk) _2026-05-19 · **Sponsored**_ Personal posts on agentic coding, moshcode CLI, and security findings. ## [Fidlock Hip Pack with Magnets](https://www.bikehugger.com/posts/fidlock-hip-pack-with-magnets/) _2026-05-18 · Byron · Bike Hugger_ The Fidlock Hip Pack with magnets instantly became my go-to choice. I’m picky about hip packs—like the princess and the pea. Fidlock has always seen… The post Fidlock Hip Pack with Magnets appeared first on Bike Hugger . ## [Topeak PakGo GearPack II](https://www.bikehugger.com/posts/topeak-pakgo-gearpack-ii/) _2026-05-16 · Byron · Bike Hugger_ The Topeak PakGo GearPack II earns its place if it solves real problems: forgotten shoes, a crushed helmet, a wet kit, or the chaos of… The post Topeak PakGo GearPack II appeared first on Bike Hugger . ## [POC Drops the Cytal Helmet](https://www.bikehugger.com/posts/poc-drops-the-cytal-helmet/) _2026-05-15 · Byron · Bike Hugger_ POC Drops the Cytal Helmet, Cadence and Raceday Collection POC just released its 2026 EF Pro Cycling limited‑edition Cytal helmet, and it’s exactly what you… The post POC Drops the Cytal Helmet appeared first on Bike Hugger . ## [Hannah Otto Kilimanjaro Ascent](https://www.bikehugger.com/posts/hannah-otto-kilimanjaro-ascent/) _2026-05-14 · Byron · Bike Hugger_ Hannah Otto’s Kilimanjaro Ascent. PEARL iZUMi athlete Hannah Otto is taking on one of the boldest bike‑mountain challenges imaginable: a single‑day ascent of Mount Kilimanjaro.… The post Hannah Otto Kilimanjaro Ascent appeared first on Bike Hugger . ## [Get Insights Into Your Claude Code Usage](https://ImproveAndRepeat.com/2026/05/get-insights-into-your-claude-code-usage/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-05-12 · Improve & Repeat_ 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. ## [How to Catch Up on the Latest Claude Code Updates](https://ImproveAndRepeat.com/2026/05/how-to-catch-up-on-the-latest-claude-code-updates/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-05-05 · Improve & Repeat_ 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. ## [What Goes on Inside of Claude Code?](https://ImproveAndRepeat.com/2026/04/what-goes-on-inside-of-claude-code/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-04-28 · Improve & Repeat_ 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. ## [Are Superpowers or GSD Better Than OpenSpec?](https://ImproveAndRepeat.com/2026/04/are-superpowers-or-gsd-better-than-openspec/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-04-21 · Improve & Repeat_ 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. ## [First (and Last?) Steps With OpenSpec](https://ImproveAndRepeat.com/2026/04/first-and-last-steps-with-openspec/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-04-14 · Improve & Repeat_ 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. ## [Why Requirements Matter So Much for AI Coding Agents](https://ImproveAndRepeat.com/2026/04/why-requirements-matter-so-much-for-ai-coding-agents/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-04-07 · Improve & Repeat_ 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… ## [Open-source Screen Sharing with Control (Sponsored)](https://crawlproof.com/a/y2gE85b0OwzD) _2026-04-07 · **Sponsored**_ WebRTC screen sharing with simultaneous mouse & keyboard control; viewers join in browser. ## [The Prototype Trap](https://ImproveAndRepeat.com/2026/03/the-prototype-trap/?utm_source=PythonFriday&utm_medium=RSS&utm_campaign=feed-syndication) _2026-03-31 · Improve & Repeat_ 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.