Build agent skills tested against real requests.
What it does
Creates and improves agent skills through test runs, benchmarks, and user feedback.
When to use it
Use when creating, editing, evaluating, benchmarking, or improving the triggering description of a skill.
How to use it
Give it a skill idea or an existing draft; it develops and revises the skill with you through testing and feedback.
Uses
Good to know
- starts helper agents, number unstated
- starts 2 helper agents
- starts one helper agent per item, so the count depends on the work
- acts without asking
- works out of sight
Latest review
What you need · 4
Python runs the bundled benchmark aggregation and review scripts.
The optional description-optimization workflow requires the claude CLI and its noninteractive claude -p command.
Access · 5
This skill
Claude
Write
Sends skill content to Claude
Google Fonts
Read
Loads fonts from Google Fonts