★ 0 · Updated 2026-09-30
Runs unbiased subagents through scenarios, evaluates outputs with self-reports and metrics, and iteratively improves prompts until progress plateaus.
Browse skills that use this input.
★ 0 · Updated 2026-09-30
Runs unbiased subagents through scenarios, evaluates outputs with self-reports and metrics, and iteratively improves prompts until progress plateaus.