主观题评分标准(初高中语英作文+语文阅读理解)

文科主观题智能批改评分系统 — 支持多学科、可进化评分标准。触发词：批改作业、打分、评分标准、作业批改报告。

Security Scan

The skill's files and runtime instructions are consistent with a classroom essay-grading tool: it reads/writes local scoring-standard JSON files and produces reports; it does not request external credentials or install code from outside sources.

Purpose & Capability

Name/description (智能批改评分) match the included assets: multiple criteria/*.json rating schemas and a SKILL.md describing reading/creating those files and generating reports. No unrelated credentials, binaries, or installs are requested.

Instruction Scope

SKILL.md instructs the agent to read/create/update files in the local criteria/ directory and to accept student answers as text or images (implying OCR). That scope is appropriate for a grader, but it implies the skill will persist teacher-provided modifications and may handle student PII (names/answers/images). The instructions do not reference external endpoints, but they do allow automatic mutation of the local criteria files — confirm you expect the skill to persist changes.

Install Mechanism

Instruction-only skill with no install spec and no code to download or execute. This minimizes supply-chain risk.

Credentials

The skill requests no environment variables, credentials, or external config paths. The only requested resources are local JSON files under criteria/, which align with the declared purpose.

Persistence & Privilege

The skill will write/update criteria/*.json to implement the 'standard evolution' feature. That is reasonable, but it means teacher inputs and any automatic changes are persisted inside the skill bundle (or the agent's workspace). Review where those files are stored and who can access them.

Assessment

This skill appears to be what it claims: a local grading helper that reads/writes scoring-standard JSONs and produces annotated reports. Before installing, consider: (1) Data/privacy — student names, essays, and images may be processed and stored; confirm where criteria/ and generated reports are saved and who can access them. (2) OCR/external services — SKILL.md mentions image input but does not specify whether OCR uses local model capability or calls external APIs; verify image processing is local if you need to avoid sending student images off-site. (3) Persistent edits — teacher-provided changes to scoring standards are automatically appended to criteria/*.json; if you want change control, require manual review or backups before allowing automatic writes. (4) Output format — highlights/colouring may embed markup; check how reports are rendered and whether any exported files could leak sensitive info. If these points are acceptable or mitigated (storage location, access controls, manual review for standard updates), the skill is coherent and reasonable to use.

grading-pro — 主观题智能批改评分系统

核心能力

1. 智能评分 — 读取评分标准，对照学生答案逐项打分
2. 错误分析 — 指出错误类型（语言/逻辑/格式），给出改进建议
3. 优化范文生成 — 基于学生答案主题和内容，生成符合评分标准的高分范文（含亮点句型/词汇升级/结构优化）
4. 标准进化 — 支持教师随时补充新评分标准，自动存档记录

---

评分标准数据库

路径：criteria/

文件	适用场景
english_writing_junior.json	初中英语书面表达（满分15：内容5+语言5+结构5+印象分1）
english_writing_senior.json	高中英语书面表达（满分25：五档评分制+官方细则/高分秘诀/九种连贯连接）
english_practical_senior.json	高中英语应用文（满分15：六档评分制）
english_continuation_senior.json	高中英语读后续写（满分25：五档评分制）
chinese_essay_junior.json	初中语文作文（满分60：基础40+发展15/基准分42/阅卷特点/注意事项14条）
chinese_essay_senior.json	高中语文作文（满分60：六档分类/议论文记叙文细则/八字方针/一类卷二类卷标准）
chinese_reading_senior.json	高中语文阅读理解（含五类题型评分细则）
chinese_reading_junior.json	初中语文阅读理解（含记叙文/说明文/议论文答题模板和公式）

---

新增评分标准

在 criteria/ 目录下新建 .json 文件，命名格式：科目_年级.json（如 physics_senior.json）。

文件需包含以下核心字段：

{
  "name": "学科名称",
  "version": "1.0.0",
  "updated_at": "YYYY-MM-DD",
  "subject": "subject_key",
  "grade": "初中/高中",
  "full_score": 满分,
  "exam_type": "题目类型",
  "description": "评分标准描述",
  "criteria": [
    {
      "id": "dimension_id",
      "name": "维度名称",
      "name_cn": "中文名",
      "max_score": 分值,
      "description": "评判说明",
      "grade_rules": [
        { "range": [最高, 最低], "label": "等级", "description": "具体描述" }
      ]
    }
  ]
}

直接添加文件即可，AI 批改时会自动读取。

---

评分流程

1. 接收题目 + 评分标准 + 学生答案
   ↓
2. 读取 / 创建对应评分标准
   ↓
3. 逐项评分（得分点 × 得分理由）
   ↓
4. 生成错误清单 + 改进建议
   ↓
5. 生成优化范文：基于学生答案的主题和内容，
   用更高级的词汇/句型/结构重写，达到评分标准的高分要求
   ↓
6. 询问教师是否补充标准 → 更新 criteria/*.json

优化范文生成规则

• 不改变主题：范文必须严格围绕学生答案的原始主题
• 保留可取之处：学生答案中用得好的词汇和表达，在范文中保留并适当提升
• 逐条改正错误：针对报告中标注的每处错误，在范文中用正确表达替换
• 符合评分标准：范文应达到该评分标准的**高分档（12-15分）**水平
• 标注亮点：范文中高光词汇和复杂句型用彩色标注，方便学生对照学习

---

输入格式

{
  "subject": "english_writing | chinese_essay | math_proof | custom",
  "grade": "初一 | 初二 | 初三 | 高一 | 高二 | 高三",
  "title": "题目名称",
  "full_score": 15,
  "criteria": [{ "name": "内容", "max": 8, "rules": "..." }],
  "student_answer": "学生答案文本",
  "question": "题目内容",
  "student_name": "学生姓名（可选）"
}

或者直接发图片/文本，AI 自动识别并匹配套餐。

---

进化机制

每次批改后，教师可补充新评分标准：

老师说："以后英语作文还要加一项：卷面分2分"
→ 自动追加到 criteria/english_writing.json
→ 记录更新时间：YYYY-MM-DD
→ 下次批改自动生效

---

作文的报告结构：

1. 总分卡片（各项得分一览）
2. 学生原文（错误处红色下划线标注）
3. 错误详列（编号 + 错误内容 + 正确表达）
4. 优化范文（高分范文对照，高光标注亮点词汇和句型）
5. 改进建议 + 综合评语

---

使用示例

用户：帮我批改这篇英语作文
用户：[发送作文图片]
AI：识别完成，请提供评分标准（或使用默认标准）
用户：满分15分，内容8语言8结构4
AI：[读取english_writing.json] → 开始评分 → 生成报告