Terrarium: Multi-turn data engine for evaluating and optimizing LLM agents in living environments.
Skill Claude CodeCodex
Guide for writing Terrarium tasks. Use this skill when the user wants to create a new task.py, define checkers, use capabilities (email, calendar, workspace, postgres, notion, googlesheets), design multi-stage agent workflows, or integrate their own scenario into Terrarium. Activate whenever someone mentions writing…
Skill Claude CodeCodex
Guide for running agent tasks with Terrarium. Use this skill when the user wants to configure a job, choose agents, run tasks via CLI or Python API, understand results and metrics, or troubleshoot execution issues. Activate whenever someone mentions running tasks, configuring agents, job TOML files, trial results…