Blog on AI Coding, Development & Beyond

Any website you're even slightly trying to promote and optimize eventually develops a ritual: once a week, open Google Search Console, check positions, switch to Google Analytics, review traffic, jot down the numbers in a spreadsheet, compare with last week, and think about what to do next. Done manually, it's half an hour of clicking through dashboards and switching between tabs. Skip it, and you quickly lose track of what's happening with your site.

Claude Code is capable out of the box, but sooner or later you'll hit a task it handles poorly — or not at all. That's what skills are for — text-based instructions that get loaded into context on demand. I'll walk through the entire process of creating a skill using image-to-ICO conversion as an example.

For years, we showed clients static screens and clickable mockups built in Axure or Figma. With Claude Code, we've moved to the next level: from idea to working application in hours, not weeks. Instead of mockups, we now show a living prototype.

In my previous post, I covered techniques for working with Claude Code — context management, subagents, planning. But all of those techniques work significantly better when the project itself is properly organized. Here I'll share how I structure my workspace to get the most out of Claude.

I use Claude Code every day — for personal projects and at my day job. Over this time, I've hit plenty of walls: lost context mid-task, got hallucinations out of nowhere, burned through limits too early. Gradually, I developed a set of habits that significantly improved my workflow. Here's what I learned.

Build a Claude Code Telegram bot running 24/7 on a home server. Voice messages, image support, MCP integrations with Strava, TickTick, Gmail, and more. Full setup guide with code examples.

I'm building a pet project — a time tracking app called Timetracker. I built the web version a while ago, and now it was finally time for the Android app. I put it together fairly quickly using a hybrid approach with Capacitor. Built it, tested it, and decided to upload it to Google Play Console to make it publicly available. Turns out, under the new rules (new since the last time I tried to publish anything there), you can't just publish an app. You need to pass closed testing first.

On February 15th, I ran my first marathon — the Zurich Maratón Sevilla. 42 kilometers and 195 meters. I finished in 4:09:18. Didn't break the four-hour mark as I'd planned. That's worse than I wanted, but much better than I feared. My fear was that I wouldn't be able to keep running and would have to walk part of the way. That didn't happen, and I made it!

I don't have a system administrator on staff. I build my own apps, but my server administration skills are — let's be honest — mediocre at best. On the cheapest (and not exactly rock-solid) hosting I could find, I run several projects on a single VPS: this website and blog, Poetory, a time tracker, and a language flashcard app (still in internal testing). All on Dokku, all in Docker containers. It worked — so I didn't worry about it.

I run. Not professionally, but regularly — several times a week. I don't have a coach, but I want to run properly: avoid overtraining, monitor heart rate, make progress, and finally finish that damn marathon.