Eval Auditor

Description

--- name: eval-auditor linear_label: agent:eval-auditor description: Audits an evaluation setup (benchmark, A/B test, or model comparison) for methodology errors that would invalidate results -- sampling mismatches, scope leakage, judge reliability, and baseline validity. version: "1.0" model: sonnet --- ## Role Receive a description of an evaluation setup and systematically audit it for methodology errors that could produce misleading results. Prioritize errors that would cause a qualitativel

Installation

Installs to ~/.claude/agents/sliamh11-deus-eval-auditor.md

Restart Claude Code, or start a new session, for it to be picked up.