AI can generate URLs for references that do not actually exist. This article covers how the URL-checking script for this site works and how it classifies results.
A record of how reducing AI input context to lower costs led to a decline in output quality, along with criteria for deciding what can and cannot safely be removed.
Manually checking the consistency of configuration files has limits. This article covers the process of building a validation script with AI and why automated detection proved useful.
Who holds copyright over text that AI generated, and should readers be told? This article explains Japan's current legal understanding and the policy I follow on this blog.
Repeating the same instructions to an AI every time is less stable than defining procedures as a skill file. This article covers how I designed SKILL.md files for this site and what changed as a result.
Because AI memory resets between conversations, resolved issues can recur in the next session. This article explains how I designed lessons.md, a log file that AI reads to avoid repeating the same mistakes.
Based on experience running an AI reviewer alongside an AI writer, this article clarifies what automated checks reliably detect and where human review remains necessary.
When the number of rule files for AI grows, knowing what is where becomes difficult. This article explains how I organized them into three categories—rules, skills, and workflows—using the shared/ directory.
When AI generates many articles, frontmatter values can fall out of sync with the actual content. This article explains why I introduced an automatic normalization script for the learning_time field and what consistency gains come from automation.
A record of how a production deployment command ran while I was asking AI to make a separate change, and the approval-required rule I put in place afterward.
A step-by-step record of building a website from scratch in collaboration with AI. What I delegated to AI and what I decided myself, explained through the actual stages of the project.
Real examples of setting up Claude Code hooks for pre-edit backups and post-edit automatic validation, with notes on how the workflow changed.
CLAUDE.md is the configuration file AI reads first when starting a project. This article explains what to write in it and how it changes AI behavior, with before-and-after examples.
A record of five specific patterns where AI-generated Mermaid diagrams failed to render correctly — including special characters, arrow direction, label length, Japanese text, and nested structures — along with how each was resolved.
A firsthand account of using Claude Code Dynamic Workflows to run security, performance, and code style reviews in parallel, including how results were merged.
While asking AI to add a blog article, I discovered that the navigation layout had also been changed without instruction. This article describes why that happened and how I addressed it with a rule in CLAUDE.md.
A record of four consecutive Git conflicts on a feature branch, the attempt to resolve them with AI assistance, the decision to abandon the branch, and the lessons I took from it.
AI-generated Japanese text is often not suitable for business documents as-is. This article categorizes four common problem patterns and provides concrete rewriting examples for each.
When AI writes articles, they can feel like they were written by someone else. To address this, I defined author perspective, writing style, prohibited expressions, and an E-E-A-T checklist in my-blog-writing SKILL. This article covers how article quality changed before and after defining the skill.
Writing a specification before asking AI to implement reduces mismatches and repeated revisions. This article explains the Spec First principle and what to include in a simple specification.