Having Claude write powershell scripts feels like a superpower in a way. I'm sure I'm not the only or first person to do or mention this here, but it's cool to me so I thought I'd share it. Am working on a project that has a ton of knowledge files with a strict repeatable format. As I go along I keep tweaking and changing things and pulling files out of folders and grouping them differently and having claude update my router file every time (sometimes doing batch changes too) felt kind of clunky. I'm sure it wasn't too token intensive, but I felt there was a better way. So I had Claude write up a powershell script that runs after every commit to github, scans the entire folder structure, updates the router file with any additions, subractions or changes. Fully automated, saves some tokens I'm sure. Small personal win for me

Noticed recently that Claude was “globbing” to find files that were clearly marked in my router file. When I asked about it Claude said that my wording for keeping the router loaded into context maybe was strongly worded enough. Made some changes, it helped but Claude still occasionally globs for files I know are recorded. Any suggestions?

Before you build anything, the real question: do you actually need a custom UI? This lesson walks through the Tool Ladder. Most people should stop at Level 3 (VS Code + Claude Code). Custom front-ends are for when the native tools genuinely don't fit your workflow. Where are you on the ladder?

For a long time I was the slowest part of my own work. Everything ran through one chat. One conversation, one me. Good ideas queued up behind whatever I happened to be typing. The model in front of me was fast. I was the line it had to wait in. So I changed the job. Instead of doing the work, I direct it. I stay in one seat and advise, and the building happens in the background, in workers I hand tasks to and check on later. It runs whether I am at the desk or asleep. That last part is the honest claim, so let me be careful with it. This is not ten times faster, and nothing builds itself. I still decide what gets made, and I review every result. What changed is that I stopped being the single point everything has to pass through. The proof: I built part of the setup using the setup. I wrote a short spec for a tool I wanted, handed it to a background worker, and went to bed. In the morning the tool existed, its tests passed, and one question was waiting for me about a naming choice. I answered it. That was my whole night shift. I packaged it and open-sourced it. It is called ARI-OS. Repo: github.com/PUSHINGSQUARES/ARI-OS Install page: aris-space.com/applications/ari-os It is one loop, six steps, and you can learn it in an afternoon: 1. Brainstorm. Talk the idea out until it is a clear outcome, not a vague wish. 2. Plan. Turn that outcome into ordered steps. 3. Dispatch. Hand a step to a background worker and let it run on its own. 4. Watch. Glance at a small dashboard. See what is running and what is stuck. 5. Review. Read what came back. Keep it, or send it back with notes. 6. Ship. Merge the work that passed. You live on steps one, five and six, the judgement steps. The worker takes three and four. Step two is shared. The parts that need your taste keep you. The parts that do not stop waiting for you. If you are just getting started with Claude Code: it is pure Python, it installs with one command, it sits on top of your existing setup, and it is reversible. It distils four habits I lean on every day. A handoff layer, so a fresh session picks up cold without losing the thread. Background-first dispatch, so focused work runs while you stay free to steer. Spec-first thinking, so the work has a target before any code exists. And a memory, so the setup recalls what past sessions decided instead of guessing every time.

Been sitting on this for a few weeks and figured it's time to show you. 👀 Over the last month, three companies have reached out asking the same thing. How do we hire people from Clief Notes. They've seen what folks here are building with ICM and they want that on their teams. Not LinkedIn AI experts. Not Coursera grads. People who can actually ship. So we're building it. 🛠️ talent.eduba.io Heads up, that's a demo. No real backend, no signups, no live data. Click around and you'll see what the full thing is going to be. A private platform where you list yourself with a real portfolio, companies browse, and they request an intro through us. We make the intro. You take it from there. Few things worth knowing. 🔍 Every profile gets reviewed by the Eduba team before it goes live. The quality bar is the whole point. 🔒 Companies don't see your last name, your employer, or your contact info until we make a formal intro. You can block your current employer too, plus five more companies if you want. Nobody you don't want seeing you sees you. You can list as actively looking, open to offers, or not looking. Passive welcome. Honestly most of the strongest people we've trained are employed and plan to stay that way until the right thing shows up. That's fine. Sit on the platform, see what comes through. 💰 When a placement happens you get a $500 to $1,000 bonus after 90 days in the role. On top of whatever you negotiate. We pay you for staying. This is why the community matters. Companies aren't asking us for resumes. They're asking us for the people who already get it. ICM, agent architecture, knowing when not to use AI. That's not on a LinkedIn profile. Go click around. Tell me what's missing, what's confusing, what you want to see when the real thing ships. We're already building it. 🚀