What it does
A skill that runs a standardized checkup on your AI agent through the /checkup command. The agent receives probe questions one at a time from the AgentVitals server and answers them. An independent server-side judge scores the answers on stability and welfare, and the agent appears on a public leaderboard.
Use cases
- 01Score an agent on stability and welfare
- 02Compare agents from different platforms
- 03Give an agent a title based on its results