메뉴
分析多轮评估结果评分数据，统计各项指标，计算评级等级。适用于分析评分趋势、计算S/A/B评级
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Create vertical short drama scripts covering macro construction, episode writing, precise optimization, and creative ideation using Emotional Spring Theory. Use when creating short dramas from scratch, optimizing existing script dialogue and pacing, designing story outlines with suspense hooks, or brainstorming slap-in-the-face scenes and character biographies.
Evaluate film and TV scripts across ideological, artistic, and entertainment value dimensions, producing structured scoring reports with follow-up recommendations. Use when assessing script development quality, determining modification direction, reviewing scripts before project approval, or benchmarking screenwriter capabilities.
Evaluate and score story text across market potential, innovation attributes, and content highlights dimensions, producing structured scoring reports with development recommendations. Use when conducting novel initial screening, assessing IP adaptation potential, scoring stories for multi-dimensional quality comparison, or guiding story creation and optimization direction.
Analyze five core story elements — genre type, story summary, character biographies, character relationships, and major plot points — producing a structured comprehensive report with optional mind map. Use when preparing for script adaptation, conducting deep story analysis, creating story development documentation, or evaluating overall story quality and market potential.
Orchestrate the full plot-point dramatic function analysis pipeline — text preprocessing, parallel segment analysis, result integration, and report generation — for long-form story content. Use when analyzing plot points and dramatic functions in long texts, producing structured dramatic analysis reports, or coordinating multi-step story analysis workflows.
基于故事文本分析人物特征，生成详细的人物小传。适用于深度理解故事人物设定、为演员塑造角色提供参考、为剧本创作建立人物档案
| name | score-analyzer |
| description | 分析多轮评估结果评分数据，统计各项指标，计算评级等级。适用于分析评分趋势、计算S/A/B评级 |
| category | novel-screening |
| version | 2.1.0 |
| last_updated | "2026-01-11T00:00:00.000Z" |
| license | MIT |
| compatibility | Claude Code 1.0+ |
| maintainer | 宫凡 |
| allowed-tools | [] |
| model | opus |
| changelog | [{"version":"2.1.0","date":"2026-01-11T00:00:00.000Z","changes":[{"type":"improved","content":"优化 description 字段，使其更精简并符合命令式语言规范"},{"type":"changed","content":"模型更改为 opus"},{"type":"improved","content":"优化功能、使用场景、评级等级定义、统计指标、核心步骤、输入要求、输出格式的描述，使其更符合命令式语言规范"},{"type":"added","content":"添加约束条件、示例和详细文档部分"}]},{"version":"2.0.0","date":"2026-01-11T00:00:00.000Z","changes":[{"type":"breaking","content":"按照 Agent Skills 官方规范重构"},{"type":"improved","content":"优化 description，使用命令式语言，精简主内容"},{"type":"added","content":"添加 license、compatibility 可选字段"}]},{"version":"1.0.0","date":"2026-01-10T00:00:00.000Z","changes":[{"type":"added","content":"初始版本"}]}] |
分析多轮评估结果中的评分数据，统计各项评分指标，计算评级等级（S强烈关注/A建议关注/B普通）。
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
【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]
参见 {baseDir}/references/examples.md 目录获取更多详细示例:
examples.md - 包含不同评估结果（如多次高分、平均分稳定、分数波动大）的详细分析报告示例。参见 {baseDir}/references/examples.md 获取关于评分分析的详细指导与案例。
| 版本 | 日期 | 变更 |
|---|---|---|
| 2.1.0 | 2026-01-11 | 优化 description 字段，使其更精简并符合命令式语言规范；模型更改为 opus；优化功能、使用场景、评级等级定义、统计指标、核心步骤、输入要求、输出格式的描述，使其更符合命令式语言规范；添加约束条件、示例和详细文档部分。 |
| 2.0.0 | 2026-01-11 | 按官方规范重构 |
| 1.0.0 | 2026-01-10 | 初始版本 |