Create agent skills tested on real requests.
What it does
Creates and improves agent skills through test runs, performance comparisons, and user feedback.
When to use it
Use when creating, editing, testing, benchmarking, or improving the triggering accuracy of a skill.
How to use it
Tell it what a skill should do or what needs improving; it drafts or revises the skill through testing and user feedback.
Uses
Good to know
- starts helper agents, number unstated
- starts one helper agent per item, so the count depends on the work
Latest review
What you need · 4
The bundled review viewer runs with Python 3 and requires only its standard library.
The optional description-optimization workflow requires the claude CLI with claude -p support.
Access · 3
This skill
Claude
Write
Sends optimization data to Claude
eval review server
Execute
Starts a local review server