Each skill bundle packages a reusable agent behavior: a prompt, supporting files, and evaluation criteria. Browse the public catalog, review the full source, then install a private copy you can edit and experiment with.
109 published bundles ready to inspect and install
Create evals with unambiguous, programmatically verifiable correct answers
Wrap real or mock APIs into instrumented RL-ready surfaces with deterministic reset, state capture, and action logging
Design and run A/B tests comparing RL-trained agent vs. baseline in production