One Image, Many Roles: Tagging Across Semantic Axes
A picture tagged "shield" is findable by "shield." The reason it isn't also serving your security, access-control, and hardening pages is that "shield" is one flat label where meaning has several dimensions.
Designing an Image Vault: Asset, Rendition, and the One Rule That Does Most of the Work
A folder of image files doesn't scale. The moment the same picture needs three formats, two sizes, and a way to be found, you need a model, and it's smaller than you'd think.
Making a Claude Code Skill Trigger Reliably — and How to Measure It
A perfectly written skill that never fires is worthless. Whether it fires is decided by one thing — its description — and you can measure and tune that instead of guessing.
Writing a Claude Code Skill That Mutates a Real Store
Most skills hand back text or a file — a mistake there is a bad paragraph. A skill that writes to a live database or content store is different: a mistake is duplicated, corrupted, or lost data. The build discipline has to change with it.
Where Claude Code Skills Live — and the Rule That Keeps Them Tracked
You spent an afternoon building a skill. By default it landed in a personal folder that no repo sees and no teammate has. That's real work sitting outside version control.