{"slug":"growthxai-output-eval-dataset-design","source_name":"growthxai/output-eval-dataset-design","name":"Growthxai/Output Eval Dataset Design","description":"Design diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases.","version":1,"lift":{"pass_rate_delta_pts":45.45,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":71.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-20T12:46:18.382641+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":45.45,"with_pass_pct":81.8,"without_pass_pct":36.4,"tokens_delta_pct":71.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-20T12:46:18.382641+00:00","run_id":"b61bb510-9b45-423f-b423-49f4fca86e08","latest_attempt":{"id":"b61bb510-9b45-423f-b423-49f4fca86e08","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-20T12:46:18.382641+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":"b51878f27ed92bc52df7825a7bfa8155f669effeff89190dae96957f892f01e7","install_name":"growthxai-output-eval-dataset-design","version_id":"274ccdf8-2dcd-400b-98ea-e0f24521f299","body_sha256":"b51878f27ed92bc52df7825a7bfa8155f669effeff89190dae96957f892f01e7","render_hash":"8433b955ac1eb33d504c62817c2ee851b1ec6178c0977c6e4a31a4f630983598","raw_url":"https://app.decimal.ai/s/growthxai-output-eval-dataset-design/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/growthxai-output-eval-dataset-design"}