★ 8 · Updated 2026-03-22
Define and run evaluations as unit tests to validate AI code against success criteria
Browse skills that share this capability.
★ 8 · Updated 2026-03-22
Define and run evaluations as unit tests to validate AI code against success criteria
★ 1 · Updated 2026-02-13
Creates Architecture Decision Records (ADRs) documenting technical decisions with alternatives, rationale, and consequences
★ 509 · Updated 2026-02-13
Build robust backtesting systems for trading strategies with proper bias handling and cost modeling