{"slug":"yogsoth-ai-confidence-calibration","source_name":"yogsoth-ai/confidence-calibration","name":"Yogsoth AI/Confidence Calibration","description":"Calibrates confidence scores based on debate progression. Determines whether to escalate, continue, or terminate based on cumulative evidence.","version":1,"lift":{"pass_rate_delta_pts":45.45,"pass_rate_pct":72.7,"total_cases":22,"passed_cases":16,"tokens_delta_pct":-18.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T07:30:24.845621+00:00"},"skill_score":0.7273,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":45.45,"with_pass_pct":72.7,"without_pass_pct":27.3,"tokens_delta_pct":-18.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-22T07:30:24.845621+00:00","run_id":"991a1a3d-2f23-4d42-91c7-d51103582e29","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":"abf7c8e60e94d7cbeecf69743a08bfe58cfde581124ef0bad32d61a9b9d1b471","raw_url":"https://app.decimal.ai/s/yogsoth-ai-confidence-calibration/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-confidence-calibration"}