7 posts

Apr 29, 2026 · 11 min read

Why Does My Claude Code Skill Work in One Session but Fail in Another?

Apr 21, 2026 · 11 min read

Claude A Bias: What Are the Failure Modes When the Skill Designer Is Also the Tester?

Apr 16, 2026 · 16 min read

Evaluation-First Skill Development: Write Tests Before Instructions

Apr 16, 2026 · 11 min read

What Is a 'Fair-Weather Skill' That Only Works on Easy Inputs?

Apr 16, 2026 · 9 min read

What Is Evaluation-First Development for Claude Code Skills?

Apr 16, 2026 · 10 min read

What Is an evals.json File in Claude Code Skills?

Apr 16, 2026 · 11 min read

What Are Evals in Claude Code Skills?