{
  "targets": [
    {
      "name": "yao-meta-skill",
      "winner_label": "Current",
      "winner_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
      "winner_tokens": 54,
      "current_tokens": 54,
      "winner_holdout_fp": 0,
      "winner_holdout_fn": 0,
      "current_holdout_fp": 0,
      "current_holdout_fn": 0,
      "baseline_holdout_fp": 0,
      "baseline_holdout_fn": 0,
      "winner_blind_holdout_fp": 0,
      "winner_blind_holdout_fn": 0,
      "current_blind_holdout_fp": 0,
      "current_blind_holdout_fn": 0,
      "baseline_blind_holdout_fp": 0,
      "baseline_blind_holdout_fn": 0,
      "winner_blind_holdout_total_errors": 0,
      "winner_judge_blind_holdout_fp": 0,
      "winner_judge_blind_holdout_fn": 0,
      "current_judge_blind_holdout_fp": 0,
      "current_judge_blind_holdout_fn": 0,
      "baseline_judge_blind_holdout_fp": 0,
      "baseline_judge_blind_holdout_fn": 0,
      "winner_judge_blind_holdout_total_errors": 0,
      "winner_adversarial_holdout_fp": 0,
      "winner_adversarial_holdout_fn": 0,
      "current_adversarial_holdout_fp": 0,
      "current_adversarial_holdout_fn": 0,
      "baseline_adversarial_holdout_fp": 0,
      "baseline_adversarial_holdout_fn": 0,
      "winner_adversarial_holdout_total_errors": 0,
      "calibration": {
        "holdout": {
          "threshold": 0.33,
          "mean_positive_score": 0.704,
          "mean_non_trigger_score": 0.0,
          "mean_near_neighbor_score": 0.0,
          "min_positive_score": 0.465,
          "max_non_trigger_score": 0.0,
          "score_gap": 0.465,
          "threshold_margin": 0.135,
          "positive_threshold_buffer": 0.135,
          "negative_threshold_buffer": 0.33,
          "boundary_case_count": 0,
          "boundary_case_rate": 0.0,
          "risk_band": "healthy"
        },
        "blind_holdout": {
          "threshold": 0.33,
          "mean_positive_score": 0.377,
          "mean_non_trigger_score": 0.024,
          "mean_near_neighbor_score": 0.006,
          "min_positive_score": 0.374,
          "max_non_trigger_score": 0.084,
          "score_gap": 0.29,
          "threshold_margin": 0.044,
          "positive_threshold_buffer": 0.044,
          "negative_threshold_buffer": 0.246,
          "boundary_case_count": 2,
          "boundary_case_rate": 0.333,
          "risk_band": "watch"
        },
        "adversarial_holdout": {
          "threshold": 0.33,
          "mean_positive_score": 0.81,
          "mean_non_trigger_score": 0.0,
          "mean_near_neighbor_score": 0.0,
          "min_positive_score": 0.808,
          "max_non_trigger_score": 0.0,
          "score_gap": 0.808,
          "threshold_margin": 0.33,
          "positive_threshold_buffer": 0.478,
          "negative_threshold_buffer": 0.33,
          "boundary_case_count": 0,
          "boundary_case_rate": 0.0,
          "risk_band": "healthy"
        }
      },
      "judge_blind": {
        "winner": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.66,
          "rubric_version": "blind-v1"
        },
        "current": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.66,
          "rubric_version": "blind-v1"
        },
        "baseline": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.66,
          "rubric_version": "blind-v1"
        }
      },
      "family_health": {
        "holdout": {
          "family_count": 12,
          "clean_family_count": 12,
          "failing_families": [],
          "weakest_family": {
            "family": "workflow_to_skill",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_operationalize",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "judge_blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_operationalize",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "adversarial_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "adversarial_summary_translation_collision",
            "pass_rate": 1.0,
            "errors": 0
          }
        }
      },
      "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
      "ok": true
    },
    {
      "name": "team-frontend-review",
      "winner_label": "Current",
      "winner_description": "Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
      "winner_tokens": 50,
      "current_tokens": 50,
      "winner_holdout_fp": 0,
      "winner_holdout_fn": 0,
      "current_holdout_fp": 0,
      "current_holdout_fn": 0,
      "baseline_holdout_fp": 0,
      "baseline_holdout_fn": 0,
      "winner_blind_holdout_fp": 0,
      "winner_blind_holdout_fn": 0,
      "current_blind_holdout_fp": 0,
      "current_blind_holdout_fn": 0,
      "baseline_blind_holdout_fp": 0,
      "baseline_blind_holdout_fn": 0,
      "winner_blind_holdout_total_errors": 0,
      "winner_judge_blind_holdout_fp": 0,
      "winner_judge_blind_holdout_fn": 0,
      "current_judge_blind_holdout_fp": 0,
      "current_judge_blind_holdout_fn": 0,
      "baseline_judge_blind_holdout_fp": 0,
      "baseline_judge_blind_holdout_fn": 0,
      "winner_judge_blind_holdout_total_errors": 0,
      "winner_adversarial_holdout_fp": 0,
      "winner_adversarial_holdout_fn": 0,
      "current_adversarial_holdout_fp": 0,
      "current_adversarial_holdout_fn": 0,
      "baseline_adversarial_holdout_fp": 0,
      "baseline_adversarial_holdout_fn": 0,
      "winner_adversarial_holdout_total_errors": 0,
      "calibration": {
        "holdout": {
          "threshold": 0.48,
          "mean_positive_score": 0.685,
          "mean_non_trigger_score": 0.089,
          "mean_near_neighbor_score": 0.045,
          "min_positive_score": 0.496,
          "max_non_trigger_score": 0.211,
          "score_gap": 0.285,
          "threshold_margin": 0.016,
          "positive_threshold_buffer": 0.016,
          "negative_threshold_buffer": 0.269,
          "boundary_case_count": 1,
          "boundary_case_rate": 0.167,
          "risk_band": "tight"
        },
        "blind_holdout": {
          "threshold": 0.48,
          "mean_positive_score": 0.685,
          "mean_non_trigger_score": 0.177,
          "mean_near_neighbor_score": 0.226,
          "min_positive_score": 0.504,
          "max_non_trigger_score": 0.416,
          "score_gap": 0.088,
          "threshold_margin": 0.024,
          "positive_threshold_buffer": 0.024,
          "negative_threshold_buffer": 0.064,
          "boundary_case_count": 2,
          "boundary_case_rate": 0.333,
          "risk_band": "tight"
        },
        "adversarial_holdout": {
          "threshold": 0.34,
          "mean_positive_score": 0.71,
          "mean_non_trigger_score": 0.009,
          "mean_near_neighbor_score": 0.018,
          "min_positive_score": 0.544,
          "max_non_trigger_score": 0.035,
          "score_gap": 0.509,
          "threshold_margin": 0.204,
          "positive_threshold_buffer": 0.204,
          "negative_threshold_buffer": 0.305,
          "boundary_case_count": 0,
          "boundary_case_rate": 0.0,
          "risk_band": "healthy"
        }
      },
      "judge_blind": {
        "winner": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.703,
          "rubric_version": "blind-v1"
        },
        "current": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.703,
          "rubric_version": "blind-v1"
        },
        "baseline": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.703,
          "rubric_version": "blind-v1"
        }
      },
      "family_health": {
        "holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "security_and_a11y",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_premerge",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "judge_blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_premerge",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "adversarial_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "adversarial_quality_gate_review",
            "pass_rate": 1.0,
            "errors": 0
          }
        }
      },
      "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
      "ok": true
    },
    {
      "name": "governed-incident-command",
      "winner_label": "Current",
      "winner_description": "Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
      "winner_tokens": 37,
      "current_tokens": 37,
      "winner_holdout_fp": 0,
      "winner_holdout_fn": 1,
      "current_holdout_fp": 0,
      "current_holdout_fn": 1,
      "baseline_holdout_fp": 0,
      "baseline_holdout_fn": 1,
      "winner_blind_holdout_fp": 0,
      "winner_blind_holdout_fn": 0,
      "current_blind_holdout_fp": 0,
      "current_blind_holdout_fn": 0,
      "baseline_blind_holdout_fp": 0,
      "baseline_blind_holdout_fn": 0,
      "winner_blind_holdout_total_errors": 0,
      "winner_judge_blind_holdout_fp": 0,
      "winner_judge_blind_holdout_fn": 0,
      "current_judge_blind_holdout_fp": 0,
      "current_judge_blind_holdout_fn": 0,
      "baseline_judge_blind_holdout_fp": 0,
      "baseline_judge_blind_holdout_fn": 0,
      "winner_judge_blind_holdout_total_errors": 0,
      "winner_adversarial_holdout_fp": 0,
      "winner_adversarial_holdout_fn": 0,
      "current_adversarial_holdout_fp": 0,
      "current_adversarial_holdout_fn": 0,
      "baseline_adversarial_holdout_fp": 0,
      "baseline_adversarial_holdout_fn": 0,
      "winner_adversarial_holdout_total_errors": 0,
      "calibration": {
        "holdout": {
          "threshold": 0.48,
          "mean_positive_score": 0.45,
          "mean_non_trigger_score": 0.019,
          "mean_near_neighbor_score": 0.037,
          "min_positive_score": 0.08,
          "max_non_trigger_score": 0.057,
          "score_gap": 0.023,
          "threshold_margin": -0.4,
          "positive_threshold_buffer": -0.4,
          "negative_threshold_buffer": 0.423,
          "boundary_case_count": 0,
          "boundary_case_rate": 0.0,
          "risk_band": "overlap"
        },
        "blind_holdout": {
          "threshold": 0.48,
          "mean_positive_score": 0.82,
          "mean_non_trigger_score": 0.059,
          "mean_near_neighbor_score": 0.0,
          "min_positive_score": 0.645,
          "max_non_trigger_score": 0.228,
          "score_gap": 0.417,
          "threshold_margin": 0.165,
          "positive_threshold_buffer": 0.165,
          "negative_threshold_buffer": 0.252,
          "boundary_case_count": 0,
          "boundary_case_rate": 0.0,
          "risk_band": "healthy"
        },
        "adversarial_holdout": {
          "threshold": 0.34,
          "mean_positive_score": 0.907,
          "mean_non_trigger_score": 0.083,
          "mean_near_neighbor_score": 0.139,
          "min_positive_score": 0.815,
          "max_non_trigger_score": 0.277,
          "score_gap": 0.538,
          "threshold_margin": 0.063,
          "positive_threshold_buffer": 0.475,
          "negative_threshold_buffer": 0.063,
          "boundary_case_count": 1,
          "boundary_case_rate": 0.167,
          "risk_band": "watch"
        }
      },
      "judge_blind": {
        "winner": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.677,
          "rubric_version": "blind-v1"
        },
        "current": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.677,
          "rubric_version": "blind-v1"
        },
        "baseline": {
          "agreement_rate": 1.0,
          "mean_confidence": 0.677,
          "rubric_version": "blind-v1"
        }
      },
      "family_health": {
        "holdout": {
          "family_count": 6,
          "clean_family_count": 5,
          "failing_families": [
            {
              "family": "packet_assembly",
              "errors": 1,
              "pass_rate": 0.0
            }
          ],
          "weakest_family": {
            "family": "packet_assembly",
            "pass_rate": 0.0,
            "errors": 1
          }
        },
        "blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_summary_only",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "judge_blind_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "blind_summary_only",
            "pass_rate": 1.0,
            "errors": 0
          }
        },
        "adversarial_holdout": {
          "family_count": 6,
          "clean_family_count": 6,
          "failing_families": [],
          "weakest_family": {
            "family": "adversarial_single_update_collision",
            "pass_rate": 1.0,
            "errors": 0
          }
        }
      },
      "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
      "ok": true
    }
  ],
  "ok": true
}