{"slug":"growthxai-output-eval-audit","source_name":"growthxai/output-eval-audit","name":"Growthxai/Output Eval Audit","description":"Audit an existing eval suite for trustworthiness. Use when inheriting evals, suspecting evals miss real failures, or after significant pipeline changes.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":74.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-20T08:36:08.906445+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":90.9,"without_pass_pct":63.6,"tokens_delta_pct":74.7,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":19,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-20T08:36:08.906445+00:00","run_id":"c5814fd5-1bba-4f92-a407-443f7d7c0e2b","latest_attempt":{"id":"c5814fd5-1bba-4f92-a407-443f7d7c0e2b","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-20T08:36:08.906445+00:00","gate":null},"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,"total_uses":0,"total_users":0,"manifest_hash":"605f8489e5c75c99daaa10e2785d018e0b261c7d36c7a0cb8f8b3171d0ce2421","install_name":"growthxai-output-eval-audit","version_id":"699febb2-b1ca-497e-828d-a619cbbf55e3","body_sha256":"605f8489e5c75c99daaa10e2785d018e0b261c7d36c7a0cb8f8b3171d0ce2421","render_hash":"7eb482b1177686b81377d29a19813e175f426ff7929e97a3962e025353981bf9","raw_url":"https://app.decimal.ai/s/growthxai-output-eval-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/growthxai-output-eval-audit"}