evalgate · Agent Skills

evalgate

Community

evaluate-ai-change

Determine and execute the smallest defensible EvalGate workflow for an AI change, response, artifact, or non-chat model event. Use for prompts, models, tools, agents, retrieval, skills, MCP, judges, datasets, routing, safety, cost, latency, release policy, external optimization imports, or governed improvement and confirmation cycles; skip it for work proven not to affect observable AI behavior.

1h installs

9

GitHub stars

1

Updated

Oct 5