evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
The canonical home for this skill is evaluation in popey/claude-code-skills
No security review available
No security review has been published for this skill
- Repository
- popey/claude-code-skills
- Commit
a5a6601
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.