Features
Analyze scoring data from multiple rounds of evaluation results, tally various scoring metrics, and calculate rating levels (S Strong Attention / A Recommended Attention / B Ordinary).
Use Cases
- Quickly grasp the overall performance and trends of multiple rounds of evaluation results.
- Based on quantitative data, provide decision support for project initiation and IP adaptation.
- Identify high-potential works and perform S/A/B grading.
- Assist evaluators in analyzing scoring deviations and optimizing the evaluation process.
Rating Level Definitions
- S Level (Strong Attention): At least one score of 8.5, or a cumulative total of at least eight scores of 8.0.
- A Level (Recommended Attention): A cumulative total of at least five scores of 8.0.
- B Level (Ordinary): Does not meet the A Level standard.
Statistical Metrics
- Number of Evaluations: Count the total number of evaluation rounds.
- Number of Valid Scores: Count the evaluation rounds that have valid scoring data.
- First Score: Record the score of the first evaluation.
- Highest Score: Record the highest score among all evaluations.
- Lowest Score: Record the lowest score among all evaluations.
- Average Score: Calculate the average score of all evaluations.
- Trimmed Mean Score: The average score after removing the highest and lowest scores.
- High Score Count Statistics: Count the occurrences of each score range (such as 8.5 and above, 8.0-8.4).
Core Steps
接收多轮评估结果
↓
提取所有评分数据
↓
统计各项评分指标
↓
计算评级等级
↓
生成综合评估报告
↓
输出结构化结果
Input Requirements
- Evaluation Results: Structured text containing scoring data from multiple rounds of evaluation (it is recommended to include at least 10 evaluation results).
- Scoring Dimensions: Clearly define the dimensions and standards on which the scoring is based.
- Special Requirements(Optional): Any specific statistical or analytical requirements.
Output Format
【评分分析报告】
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
一、评估概览
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- 评估次数：[次数]
- 有效评分：[数量]
- 评级等级：[S/A/B]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
二、评分统计
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- 首次评分：[分数]
- 最高分：[分数]
- 最低分：[分数]
- 平均分：[分数]
- 去极值平均分：[分数]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
三、评分序列
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. [分数]
2. [分数]
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
四、高分统计
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- 8.5分及以上：[次数]
- 8.0-8.4分：[次数]
- 7.5-7.9分：[次数]
- 7.4分及以下：[次数]
Constraints
- The input evaluation data must contain explicit scores in order to perform statistical analysis.
- The report content must be objective and fair, generated based on data, and must not make subjective judgments.
- Ensure that the calculation results are accurate and error-free.
Examples
See {baseDir}/references/examples.md directory for more detailed examples:
examples.md- Detailed analysis report examples containing different evaluation results (such as multiple high scores, stable average scores, and large score fluctuations).
Detailed Documentation
See {baseDir}/references/examples.md for detailed guidance and cases on scoring analysis.
Version History
| Version | Date | Changes |
|---|---|---|
| 2.1.0 | 2026-01-11 | Optimized the description field to make it more concise and compliant with imperative language conventions; changed the model to opus; optimized the descriptions of features, use cases, rating level definitions, statistical metrics, core steps, input requirements, and output format to make them more compliant with imperative language conventions; added constraints, examples, and detailed documentation sections. |
| 2.0.0 | 2026-01-11 | Refactored according to official specifications |
| 1.0.0 | 2026-01-10 | Initial version |