{"slug":"yogsoth-ai-ladder-quality-order","source_name":"yogsoth-ai/ladder-quality-order","name":"Yogsoth AI/Ladder Quality Order","description":"Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.","version":1,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":9.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-07T10:06:36.682038+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":81.8,"without_pass_pct":45.5,"tokens_delta_pct":9.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-09-07T10:06:36.682038+00:00","run_id":"82f3e668-5659-4f94-9fa3-16bf96557aa9","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":"f346685d9d34b3bbd02d7d41ed977a63827e30ccfb363265129510b7615dc37d","raw_url":"https://app.decimal.ai/s/yogsoth-ai-ladder-quality-order/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-ladder-quality-order"}