What makes 美光车险PDF转Excel notable?

1.4K downloads. Trust evidence available

How should 美光车险PDF转Excel be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

美光车险PDF转Excel

Automatically extracts 14 key fields from Meiguang car insurance PDFs for 8 insurers and outputs data in Excel format. Skill: 美光车险PDF转Excel Owner: cc19960203cc Summary: Automatically extracts 14 key fields from Meiguang car insurance PDFs for 8 insurers and outputs data in Excel format. Tags: car-insurance:2.0.0, excel:2.0.0, insurance:2.0.0, latest:5.7.5, pdf:2.0.0 Version history: v5.7.5 | 2026-05-26T08:16:27.895Z | user 修复中煤保险手机号提取问题；新增中银保险支持；PDF文本缓存优化（速度提升45%） v5.7.3 | 2026-05-11T06:08:37.045Z | user 被保险人手机号黑名单(15063838021/183545

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

5.7.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 5.7.5release · observed May 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17d5bt2b116be8ef60yh30n4183kjz2:meiguang-car-insurance

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-cc19960203cc-meiguang-car-insurance/snapshot"

Documentation

CLAWHUB

24,091 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

# 美光车险PDF转Excel v5.7.5

从车险保单 PDF 自动提取 15 个字段，输出 Excel。支持 14 家保险公司，全量覆盖交强险/商业险/驾乘险/非车险。

## 支持的保险公司和险种

| 保险公司 | 险种 |
|---------|------|
| 中国人民财产保险股份有限公司 | 交强险、商业险、如意行（PEBS） |
| 中国太平洋财产保险股份有限公司 | 交强险、商业险、驾意险（畅行保） |
| 中国大地财产保险股份有限公司 | 交强险、商业险、驾意险、团体意外险（安行如意保） |
| 中国平安财产保险股份有限公司 | 交强险、商业险、车主尊享保障 |
| 浙商财产保险股份有限公司 | 交强险、商业险 |
| 阳光财产保险股份有限公司 | 驾乘人员团体意外险 |
| 亚太财产保险有限公司 | 交强险、商业险、非车险 |
| 华海财产保险股份有限公司 | 交强险、商业险、驾意险 |
| 利宝保险有限公司 | 交强险、驾乘人员意外伤害保险（合并PDF拆分） |
| 太平财产保险有限公司 | 交强险、商业险、驾乘险 |
| 泰山财产保险股份有限公司 | 交强险、商业险、驾乘险 |
| 安华农业保险股份有限公司 | 交强险、商业险、驾乘险 |
| 中煤财产保险股份有限公司 | 交强险、商业险、驾乘险 |
| 中银保险有限公司 | 交强险、商业险 |

## 提取字段（15个）

1. Filename（源文件名）
2. 签单时间
3. 保险公司名称（标准化全称）
4. 保单号
5. 被保人姓名
6. 被保险人证件号
7. 车辆使用性质
8. 车架号（VIN，17位）
9. 车辆型号名称
10. 被保险人手机号
11. 车牌号码
12. 险种名称原始
13. 实收保费
14. 车船税
15. 保险起期

## 使用方法

直接运行：
```bash
python scripts/run_extract.py
```

输入：`C:\Users\Administrator\Desktop\车险保单`
输出：`C:\Users\Administrator\Desktop\车险保单提取结果_v5.xlsx`

## 配置

在 `scripts/run_extract.py` 顶部修改：
```python
PDF_FOLDER = r"C:\你的PDF文件夹路径"
OUTPUT_FILE = r"C:\输出文件路径.xlsx"
```

## 已知限制

- 平安车主尊享保障：pymupdf 中文全乱码，部分字段可能为空（待修复）
- 部分商业险 PDF 无实收保费数据（pdfplumber 文本提取不稳）

## 更新日志

### v5.7.5 (2026-05-26)
- 修复中煤保险手机号提取问题

### v5.7.4 (2026-05-26)
- 新增中银保险有限公司支持（交强险、商业险）

### v5.7.0 (2026-05-07)
- 新增华海财产保险支持（交强险/商业险/驾意险）
- 代码优化：抽取公共字段提取函数 `_extract_common_fields()`，三大解析器减~350行重复代码
- PDF 表格缓存 `_TABLE_CACHE`，同一PDF只打开一次，I/O降低80%+
- `clean_data` 拆分为5个独立清洗函数
- trace.log 改用 logging 模块
- 修复6个代码质量问题（函数重复定义、中文数字映射bug、float逗号处理等）
- 全量 98 条记录，15 字段覆盖率 100%（车船税除外，商业险/驾乘险正常无此字段）

### v5.6.0 (2026-05-07)
- 新增利宝保险专用解析器（交强险+驾乘险合并PDF拆分为2条记录）
- 新增平安车主尊享保障、阳光驾乘险支持
- 修复大地安行如意保手机号跨行匹配问题
- 修复大地交强险车辆型号名称跨行提取问题
- 全量 98 条记录字段覆盖率 100%

### v5.2.0 (2026-05-06)
- 修复 PLATE_INSURED_LOOKUP 未定义导致脚本崩溃
- 车船税异常大值修复

### v5.0.7 (2026-04-29)
- 阳光驾乘险、平安尊享保障险种名称提取修复
- 平安交强险车船税修复
- 太平洋畅行保专用解析器

### v3.0.1 (2026-04-22)
- 字节级正则绕过 plumber text 编码损坏问题
- 签单时间提取器独立化

### v1.2.0 (2026-04-18)
- 新增大地安行如意保专用解析函数
- 被保人姓名支持投保人名称回退

_meta.json

{
  "ownerId": "kn70kp2n23bmk3h02t419g9zas83b321",
  "slug": "meiguang-car-insurance",
  "version": "5.7.5",
  "publishedAt": 1779783387895
}

skill-card.md

## Description:

Extracts key data from Meiguang car insurance PDF policies across supported Chinese insurers and outputs the results as an Excel workbook.

This skill is ready for commercial/non-commercial use.

## Publisher:

[cc19960203cc](https://clawhub.ai/user/cc19960203cc)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operations users handling authorized vehicle-insurance policy PDFs use this skill to extract policy, insured-person, vehicle, premium, and coverage-start fields into a spreadsheet for review or downstream processing.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Insurance PDFs can contain sensitive personal, vehicle, and policy data that is exported into an unprotected spreadsheet.

Mitigation: Process only authorized PDFs, write the workbook to a protected location, restrict access to the output, and delete generated files when they are no longer needed.

Risk: Source PDFs are untrusted inputs and may trigger parser or dependency issues during extraction.

Mitigation: Run the extraction in a least-privileged environment with current PDF-processing dependencies and keep source files isolated from unrelated data.

Risk: The optimize_*.py helper scripts rewrite run_extract.py when executed.

Mitigation: Do not run optimization scripts unless code rewriting is intentional; keep a backup or version-controlled copy before using them.

Risk: Known PDF text-extraction limitations may leave some fields empty or inaccurate for specific insurers or document encodings.

Mitigation: Review the generated spreadsheet against source PDFs before relying on extracted values for operational decisions.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/cc19960203cc/skills/meiguang-car-insurance)

## Skill Output:

**Output Type(s):** [guidance, shell commands, configuration, code, files]

**Output Format:** [Markdown guidance with Python command examples; the extraction script writes an .xlsx workbook.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Default input and output paths are configured in scripts/run_extract.py and should be changed before use.]

## Skill Version(s):

5.7.5 (source: server evidence and artifact documentation)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 21h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular