analyzing-new-energy-trucks

分析新能源货车保险业务数据,识别高风险机构和业务类型。在处理新能源货车承保数据、风险评估报告或制定承保策略时使用。

16 stars

Best use case

analyzing-new-energy-trucks is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

分析新能源货车保险业务数据,识别高风险机构和业务类型。在处理新能源货车承保数据、风险评估报告或制定承保策略时使用。

Teams using analyzing-new-energy-trucks should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/analyzing-new-energy-trucks/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/cli-automation/analyzing-new-energy-trucks/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/analyzing-new-energy-trucks/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How analyzing-new-energy-trucks Compares

Feature / Agentanalyzing-new-energy-trucksStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

分析新能源货车保险业务数据,识别高风险机构和业务类型。在处理新能源货车承保数据、风险评估报告或制定承保策略时使用。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 新能源货车保险分析

## 核心功能

专项分析新能源货车(`is_new_energy_vehicle=True` 且 `business_type_category` 包含"货车")的保险业务表现:

- ✅ 多周趋势分析(赔付率、保费规模、案均赔款)
- ✅ 机构风险评级(按赔付率分档)
- ✅ 业务类型深度钻取(车型、险别、续保状态)
- ✅ 异常波动检测(单周暴涨、连续恶化)

## 立即使用

```python
# 快速分析流程
from analyze_new_energy_trucks import NewEnergyTruckAnalyzer

analyzer = NewEnergyTruckAnalyzer(
    data_folder="2025年保单",
    start_week=28,
    end_week=43
)

# 加载数据
available_weeks, missing_weeks = analyzer.load_data()

# 计算指标
weekly_kpis = analyzer.calculate_weekly_kpis()

# 分析区域
regional_analysis = analyzer.analyze_regional_performance()

# 生成报告
report = analyzer.generate_report(
    weekly_kpis,
    regional_analysis,
    business_analysis,
    trend_analysis,
    problem_weeks
)
```

## 关键指标阈值

| 指标 | 良好 | 关注 | 预警 | 高危 |
|-----|------|------|------|------|
| 赔付率 | <60% | 60-70% | 70-80% | >80% |
| 出险率 | <25% | 25-50% | 50-100% | >100% |
| 边际贡献率 | >8% | 4-8% | 0-4% | <0% |
| 案均赔款 | <5k | 5k-8k | 8k-10k | >10k |

## 分析维度

### 1. 时间趋势分析

**关键指标周度跟踪**:
- 赔付率走势(累计值)
- 保费规模增长(周度对比)
- 案均赔款波动(检测突增)
- 出险率变化(风险暴露)

**异常检测规则**:
```python
# 单周暴涨
if current_loss_ratio > prev_loss_ratio * 1.15:
    alert("赔付率单周暴涨>15%")

# 案均突增
if current_avg_claim > period_avg * 1.5:
    alert("案均赔款异常")
```

### 2. 区域风险评估

**机构分档**:
- 🟢 低风险: 赔付率 < 70%
- 🟡 中风险: 赔付率 70-80%
- 🟠 高风险: 赔付率 80-100%
- 🔴 极危: 赔付率 > 100%

**重点关注条件**:
- 赔付率 > 80% 且保费规模 > 50万
- 连续3周赔付率恶化
- 边际贡献率 < -30%

### 3. 业务类型钻取

**车型分类**:
- 2吨以下营业货车(主力业务)
- 2-10吨营业货车
- 10吨以上营业货车
- 非营业货车

**险别结构**:
- 主全险(组合险)
- 交三险(交强险第三者)
- 单独险别

## 输出报告结构

```markdown
# 新能源货车分析报告 - {年份}第{X-Y}周

## 一、执行摘要
### 核心结论
### 关键指标

## 二、趋势分析
### 分析周期表现
### 核心发现
### 各周详细指标

## 三、异常周次识别
### 第X周 - [问题描述]

## 四、区域表现分析
### 各机构业务表现
### 高风险机构清单

## 五、战略建议与行动计划
### 🚨 立即行动(24小时内)
### ⏰ 本周内完成(7天)
### 📊 中期优化(1个月内)
### 🎯 长期战略(3个月内)

## 附录:分析说明
```

## 实用脚本

### 快速执行分析

```bash
# 运行分析脚本
python3 analyze_new_energy_trucks.py

# 自定义周期
# 修改脚本中的 START_WEEK 和 END_WEEK 变量
```

### 数据质量检查

```bash
# 检查新能源货车数据量
grep -c "True.*货车" 2025年保单/2025保单第*周*.csv

# 验证数据完整性
ls 2025年保单/2025保单第{28..43}周*.csv 2>/dev/null | wc -l
```

## 常见问题

### Q1: 赔付率超过100%正常吗?

**A**: 对于新能源货车,这是常见现象,原因包括:
- 电池更换成本高(占车价30-40%)
- 充电基础设施不完善导致事故增多
- 维修网络稀缺,修理成本高
- 技术不成熟,故障率高

### Q2: 如何识别电池相关理赔?

**A**: 简化识别方法:
```python
# 使用案均赔款作为代理指标
battery_related = df[df['reported_claim_payment_yuan'] > 50000]
# 大于5万元的理赔很可能涉及电池
```

### Q3: 缺失周次如何处理?

**A**: 脚本自动处理:
- 跳过缺失周次
- 在报告中标注
- 不影响其他周次分析

### Q4: 如何对比传统货车?

**A**: 需要单独分析传统货车数据:
```python
# 筛选传统货车
traditional_trucks = df[
    (df['is_new_energy_vehicle'] == False) &
    (df['business_type_category'].str.contains('货车'))
]
```

## 风险识别规则

### 立即警报条件

```python
# 机构级别
if loss_ratio > 150:
    trigger_alert("极危:机构赔付率>150%")

# 周度波动
if week_over_week_change > 50:
    trigger_alert("警告:单周赔付率暴涨>50%")

# 业务质量
if claim_frequency > 100:
    trigger_alert("关注:出险率>100%,多次出险")
```

### 监控指标清单

- [ ] 赔付率 > 80%
- [ ] 出险率 > 100%
- [ ] 案均赔款 > 10,000元
- [ ] 边际贡献率 < 0%
- [ ] 单周赔付率增幅 > 20%
- [ ] 连续3周恶化趋势

## 参考资源

详细参考文档:
- `reference/kpi_definitions.md` - KPI定义和计算公式
- `reference/risk_thresholds.md` - 风险阈值标准
- `reference/new_energy_insights.md` - 新能源车险行业洞察

工具脚本:
- `scripts/analyze_new_energy_trucks.py` - 主分析脚本
- `scripts/data_validator.py` - 数据验证工具

## 更新日志

- v1.0 (2025-11-04): 初始版本
  - 基础分析框架
  - 周度趋势跟踪
  - 区域风险评估
  - 自动报告生成

Related Skills

analyzing-innovation-portfolio

16
from diegosouzapw/awesome-omni-skill

Analyze the CustomGPT.ai Labs Innovation workbook and cost tracking data to surface portfolio-level insights, trends, and recommendations for where to focus Innovation efforts.

analyzing-data

16
from diegosouzapw/awesome-omni-skill

Queries data warehouse and answers business questions about data. Handles questions requiring database/warehouse queries including "who uses X", "how many Y", "show me Z", "find customers", "what is the count", data lookups, metrics, trends, or SQL analysis.

analyzing-auto-insurance-data

16
from diegosouzapw/awesome-omni-skill

Analyzes vehicle insurance daily reports and signing lists. Use when user asks to analyze insurance data, generate business reports, check institution performance, monitor policy trends, or detect business anomalies. Handles Excel/CSV files with fields like premium, institution, customer type, and renewal status.

analyzing-git-sessions

16
from diegosouzapw/awesome-omni-skill

Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.

analyzing-branches

16
from diegosouzapw/awesome-omni-skill

Use when analyzing another branch's iteration journals to extract findings, decisions, and insights from divergent work

analyzing-branch-status

16
from diegosouzapw/awesome-omni-skill

Use when user wants detailed status report for single autonomy branch including iteration timeline and metrics progression

energy-procurement

16
from diegosouzapw/awesome-omni-skill

Codified expertise for electricity and gas procurement, tariff optimisation, demand charge management, renewable PPA evaluation, and multi-facility energy cost management.

analyzing-tdigest-metrics

16
from diegosouzapw/awesome-omni-skill

Analyze percentile metrics (tdigest type) using OPAL for latency analysis and SLO tracking. Use when calculating p50, p95, p99 from pre-aggregated duration or latency metrics. Covers the critical double-combine pattern with align + m_tdigest() + tdigest_combine + aggregate. For simple metrics (counts, averages), see aggregating-gauge-metrics skill.

analyzing-protocols

16
from diegosouzapw/awesome-omni-skill

Analyzes network protocol implementations to identify parsing vulnerabilities, state machine issues, and protocol-level security problems. Use when analyzing network servers, protocol handlers, or investigating protocol implementation bugs.

analyzing-projects

16
from diegosouzapw/awesome-omni-skill

Analyzes codebases to understand structure, tech stack, patterns, and conventions. Use when onboarding to a new project, exploring unfamiliar code, or when asked "how does this work?" or "what's the architecture?"

analyzing-apm-data

16
from diegosouzapw/awesome-omni-skill

Monitor application performance using the RED methodology (Rate, Errors, Duration) with Observe. Use when analyzing service health, investigating errors, tracking latency, or building APM dashboards. Covers when to use metrics vs spans, combining RED signals, and troubleshooting workflows. Cross-references working-with-intervals, aggregating-gauge-metrics, and analyzing-tdigest-metrics skills.

analyzing-test-coverage

16
from diegosouzapw/awesome-omni-skill

Creates and analyzes tests using Vitest and MSW patterns. Generates test builders, mocks repositories, and configures integration tests. Triggers on: write tests, test coverage, Vitest, MSW mock, vi.fn, vi.mock, unit test, integration test, test builder, mock setup, test failure.