{"slug":"archive228-evaluator-calibration","source_name":"archive228/evaluator-calibration","name":"Archive228/Evaluator Calibration","description":"Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.","version":1,"lift":{"pass_rate_delta_pts":43.48,"pass_rate_pct":78.3,"total_cases":23,"passed_cases":18,"tokens_delta_pct":4.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-16T00:47:17.683359+00:00"},"skill_score":0.7826,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":43.48,"with_pass_pct":78.3,"without_pass_pct":34.8,"tokens_delta_pct":4.3,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-16T00:47:17.683359+00:00","run_id":"feb778ff-53d5-4a18-8795-5ace02065a45","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":"MIT","install_count":0,"manifest_hash":"0f35b389c4e907ec9ef4ee685ff20b0862163eca3794a1e5cf6461ce28f71294","raw_url":"https://app.decimal.ai/s/archive228-evaluator-calibration/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/archive228-evaluator-calibration"}