It's been about a month since I installed OpenClaw for the first time. I'm the type who does a lot of "let's see how this feels" before spending real money on a hobby. So while everyone else was buying a Mac mini to set things up, I installed OpenClaw on my personal MacBook first and… Continue reading Moving OpenClaw to a Mac mini
Now that I've set things up so I can collaborate with my OpenClaw AI assistant, N.I.C.K., via GitHub Issues, it's time to teach N.I.C.K. how to publish posts on each platform. I can't exactly keep telling GitHub, issue after issue, "this is how you upload to Facebook." In OpenClaw—and now in Claude Code as well—there's… Continue reading Building a Writing Workflow Automation (Part 2)
Since mid-January, I've been following this writing pattern: Post to Facebook first, then upload the same content to Instagram, translate it to English and post to my WordPress blog, then post the same content to LinkedIn. There are additional rules for edge cases—daily life posts only go to Facebook and Instagram, longer posts get split… Continue reading Building a Writing Workflow Automation (Part 1)
Because there's no clear owner, I'm currently responsible for a few repositories. Most of them are data-pipeline related—projects that had been drifting without proper history, or ones I inherited after the original maintainer left and there was no obvious handoff target. Lately, as I've been studying Claude Code and SDD, I realized these repos couldn't… Continue reading I Asked Claude Code for Optimization. It Found a Defect.
About a week ago, I tried agent coding through OpenClaw but paused it after some initial tests. It seemed to work, but I wasn’t convinced there was enough benefit. Over the past few days, though, my mindset shifted—I decided to trust AI a bit more. Also, given the timing, I figured I should try everything… Continue reading On the Case Where My AI Agent Asked for tmux
There are two major concerns people raise about the risks of adopting OpenClaw. One is security risk—attacks from outside and related exposure. The other is the risk of the AI taking dangerous actions on its own. This second category includes both security incidents and operational risks such as unintended data deletion. I almost ran into… Continue reading “Delete This” — And My AI Almost Did the Wrong One
I was curious how OpenClaw skills are built, so I gave it a try. After asking Gemini, I learned that the basic approach is to define the behavior in a SKILL markdown file. If needed, you can also include a simple script alongside it. Pretty straightforward. While thinking about what to build, I decided to… Continue reading Dooray Messenger Hook Skill for OpenClaw
The installation itself wasn’t difficult. Many of the terms were unfamiliar, so I skipped most of the settings or postponed them for later, and focused only on what seemed essential—setting up the model. At the very least, it needed to be able to hold a conversation. I initially configured it using a subscription token obtained… Continue reading OpenClaw: Day 1
While this may not be an early move, I’ve finally stepped into SDD (Spec-Driven Development). I’ve been hearing for quite some time about the idea of aggressively delegating coding to AI. I even ran a few experiments myself. Still, I believed that fully entrusting a large project to AI wasn’t quite realistic yet. I knew… Continue reading Stepping into SDD (Spec-Driven Development)
It just occurred to me that I should try Unity. I used to write code using a combination of Python and pygame when creating data visualization videos, but the limitations were clear—it was strictly 2D. Then it suddenly struck me: Unity is a tool well known for 3D game development. Why couldn’t it be used… Continue reading A Taste of Unity
Kirin's Technology Essay 