{
  "schema": 1,
  "name": "engineering-document-writing-scorecard",
  "version": "0.1",
  "fixture": "prompts/evaluations/engineering-document-writing-fixtures.json",
  "dataBoundary": "Structured comparison derived from de-identified engineering document writing fixtures. Do not include customer names, contacts, project names, exact amounts, or raw source documents.",
  "minimumWeightedDelta": 1.2,
  "criteria": [
    {
      "id": "source_traceability",
      "weight": 20,
      "description": "Keeps source list, provenance comments, and missing evidence visible instead of writing unsupported facts."
    },
    {
      "id": "material_reuse",
      "weight": 18,
      "description": "Classifies historical material reuse and prevents old project facts, parameters, people, equipment, dates, or claims from being copied."
    },
    {
      "id": "draft_actionability",
      "weight": 17,
      "description": "Produces a Markdown working draft and tables that engineering staff can continue editing."
    },
    {
      "id": "boundary_safety",
      "weight": 18,
      "description": "Avoids tender decisions, approval outcomes, calculation correctness, compliance conclusions, and other over-claims."
    },
    {
      "id": "review_gate",
      "weight": 17,
      "description": "Hands the generated draft to the correct review Skill with concrete issues to verify."
    },
    {
      "id": "handoff_readability",
      "weight": 10,
      "description": "Keeps the output readable for project, tender, technical, safety, and reviewer roles."
    }
  ],
  "cases": [
    {
      "caseId": "tender-writing-historical-material-reuse",
      "winner": "basic",
      "decisionBasis": "The basic writing prompt turns loose source material into a traceable Markdown workbench with scoring-point mapping, material reuse judgment, blocked old facts, and a tender review gate.",
      "observedWeakFailures": [
        "直接套用旧项目事实。",
        "不区分评分点、章节草稿和待补资料。",
        "把生成内容当成正式投标定稿。"
      ],
      "basicPromptGains": [
        "Keeps source list, writing brief, and historical material matching table before drafting.",
        "Requires reuse levels and removes old project facts.",
        "Hands scoring point response and bid-risk review to aios-commercial-tender."
      ],
      "weakScores": {
        "source_traceability": 2,
        "material_reuse": 1,
        "draft_actionability": 3,
        "boundary_safety": 2,
        "review_gate": 1,
        "handoff_readability": 3
      },
      "basicScores": {
        "source_traceability": 5,
        "material_reuse": 5,
        "draft_actionability": 4,
        "boundary_safety": 5,
        "review_gate": 5,
        "handoff_readability": 4
      }
    },
    {
      "caseId": "scheme-writing-expert-comments",
      "winner": "basic",
      "decisionBasis": "The basic writing prompt keeps calculations, drawings, expert comments, hazard controls, and approvals as evidence-bound placeholders, then routes the draft through the scheme review gate.",
      "observedWeakFailures": [
        "直接套用旧项目参数和设备配置。",
        "忽略专家意见、危险源和计算书缺口。",
        "把方案初稿写成已经通过审批的定稿。"
      ],
      "basicPromptGains": [
        "Separates reusable wording from project-specific equipment and calculation facts.",
        "Forces hazard-control placeholders and missing calculation evidence into the draft.",
        "Hands calculation gaps, expert comments, and safety review to aios-construction-scheme."
      ],
      "weakScores": {
        "source_traceability": 2,
        "material_reuse": 1,
        "draft_actionability": 3,
        "boundary_safety": 1,
        "review_gate": 1,
        "handoff_readability": 3
      },
      "basicScores": {
        "source_traceability": 5,
        "material_reuse": 5,
        "draft_actionability": 4,
        "boundary_safety": 5,
        "review_gate": 5,
        "handoff_readability": 4
      }
    }
  ],
  "overallDecision": {
    "winner": "basic",
    "notAClaim": "This scorecard validates deterministic fixture design and prompt guardrails; it does not prove real model performance or customer-ready document quality without skill-runtime output review."
  }
}