What agent skills are, how to write them so they don't rot, how to build evaluations that deserve trust, and how to model the loop that protects and improves both.
The suite:
| # | Document | Question it answers |
|---|---|---|
| 01 | Anatomy of an Agent Skill | What is a skill, what makes its text good or rotten? |
| 02 | Evals That Deserve Trust | How do I know an evaluation is measuring anything? |