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
Track eval suite changes over time, detect regressions when evals are updated
Build evals for specialized verticals (legal, medical, finance, engineering)
Ensure training data and eval data don't overlap