{"slug":"growthxai-output-eval-validate-judge","source_name":"growthxai/output-eval-validate-judge","name":"Growthxai/Output Eval Validate Judge","description":"Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.","version":1,"lift":{"pass_rate_delta_pts":43.48,"pass_rate_pct":95.7,"total_cases":23,"passed_cases":22,"tokens_delta_pct":51.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-20T08:38:17.642651+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":43.48,"with_pass_pct":95.7,"without_pass_pct":52.2,"tokens_delta_pct":51.8,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-20T08:38:17.642651+00:00","run_id":"61dffd13-574d-423c-b126-7f083137b62f","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"41ee015589389ad04d8f115b1797c4d3f709ed31c306dcbbaa0f32191bd308a8","raw_url":"https://app.decimal.ai/s/growthxai-output-eval-validate-judge/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/growthxai-output-eval-validate-judge"}