
Roger Bosch
•Oct 23, 2026
What agent skills are, when they are worth it and how a development team should organize them: the open standard, structure, evals, security and real cases.
A collection of blog posts about claude code

Roger Bosch
•Oct 23, 2026
What agent skills are, when they are worth it and how a development team should organize them: the open standard, structure, evals, security and real cases.

Roger Bosch
•Oct 13, 2026
A skill without evals is an assumption. Prompts that should and should not trigger it, comparing with and without the skill, and what to do when the model changes.

Roger Bosch
•Oct 2, 2026
A team's knowledge is spread across docs, GPTs, CLAUDE.md files and people's heads. How to turn it into AI skills without copying dead documentation.

Roger Bosch
•Sep 25, 2026
A Claude Code plugin bundles skills, commands and hooks. How to structure one, what each piece does and why critical rules belong in a hook, not a skill.

Roger Bosch
•Sep 18, 2026
Creating a skill is easy; getting it to trigger at the right time is not. How to write the description, the router pattern, scripts and SKILL.md mistakes.

Roger Bosch
•Jun 5, 2026
Third-party agent skills are a new supply chain. What ToxicSkills and Skill-Inject found, how an injection hides and what to check before installing.
OshyTech
Backend and data engineering focused on scalable systems, automation, and AI.
Copyright 2026 OshyTech. All Rights Reserved