← Back to Skills Marketplace
long1973m

保险条款分析

by 马龙 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
289
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install insurance-policy-parser
Description
解析医疗险条款文档并提取32个结构化字段，含14个核心字段和18个增强字段，支持PDF/DOCX/TXT格式，输出标准JSON
README (SKILL.md)

医疗险条款结构化解析器

任务目标

  • 本 Skill 用于：从医疗险条款文档中提取32个结构化字段
  • 能力包含：解析PDF/DOCX/TXT格式文档，提取Level 1核心字段（14个）和Level 2增强字段（18个）
  • 触发条件：用户提供医疗险条款文档或文本内容，需要结构化提取时

前置准备

  • 依赖说明：无特殊依赖，已内置文档解析脚本

操作步骤

  • 标准流程:
    1. 获取文档内容
      • 如果用户提供的是PDF/DOCX/TXT文件，调用 scripts/parse_document.py \x3Cfile_path> 获取纯文本内容
      • 如果用户直接输入保险条款文本，直接使用该文本
    2. 提取结构化信息
      • 根据 references/output-format.md 中的字段定义，从文档内容中提取对应信息
      • 智能体将逐项分析文档，填充以下两部分：
        • level1_core_fields: 14个绝对核心字段（年度限额、免赔额、赔付比例、续保条件等）
        • level2_enhancement_fields: 18个对比增强字段（家庭共享免赔额、特殊门诊、院外购药、CAR-T等）
      • 数据类型转换规则：
        • DECIMAL类型：金额转换为元（如"100万" → 1000000.00），比例转换为小数（如"100%" → 1.0000）
        • ENUM类型：严格使用枚举值（如免赔额单位："年"/"次"/"疾病"/"住院"）
        • BOOLEAN类型：根据表述判断（"保障"/"是" → true，"不保障"/"否" → false）
        • INT类型：直接提取数字（如"30天" → 30）
    3. 输出结果
      • 以JSON格式输出完整的结构化数据
      • Level 1字段必须填充，Level 2字段未明确说明可使用null
      • 确保所有字段类型和枚举值符合格式规范

资源索引

注意事项

  • 优先使用文档解析脚本处理文件，避免格式错误
  • 提取时保持原文含义，必要时可进行总结归纳
  • Level 1核心字段必须优先保证准确性，AI可100%提取无null风险
  • Level 2增强字段允许null，体现产品差异化
  • 严格按照数据类型转换规则处理数值、比例、枚举值
  • 确保JSON格式正确，避免语法错误

使用示例

  • 场景1：上传PDF医疗险合同
    • 调用脚本：python scripts/parse_document.py ./insurance_contract.pdf
    • 提取32个字段并输出结构化JSON
    • 核心字段示例：年度限额200万元、免赔额1万元/年、社保报销后100%赔付
    • 增强字段示例：院外购药保障、CAR-T治疗、家庭共享免赔额
  • 场景2：直接输入医疗险条款文本
    • 直接分析文本内容
    • 按格式规范输出32个字段的结构化JSON
    • 未明确说明的Level 2字段使用null表示
Usage Guidance
This skill appears coherent and focused on extracting structured fields from user-supplied insurance documents. Before installing/using it: (1) recognize it will read the full text of any uploaded document — do not supply documents containing personal/medical data unless you trust where the agent runs and how outputs are stored/transmitted; (2) ensure your environment has the required Python libraries (PyPDF2 and python-docx) or expect ImportError; (3) note it does not perform OCR on scanned images—provide selectable text PDFs or run OCR beforehand; (4) test with benign documents to confirm output matches the JSON schema and to validate edge cases; (5) be skeptical of the claimed '100% extraction' accuracy — manually review outputs for correctness.
Capability Analysis
Type: OpenClaw Skill Name: insurance-policy-parser Version: 1.0.0 The skill bundle is a legitimate tool for parsing insurance policy documents (PDF, DOCX, TXT) and extracting structured data into JSON. The Python script `scripts/parse_document.py` uses standard libraries (PyPDF2, python-docx) to extract text and contains no network calls, obfuscation, or unauthorized file access. The instructions in `SKILL.md` and `references/output-format.md` are strictly focused on the data extraction task and do not contain any prompt injection attempts or malicious commands.
Capability Assessment
✓ Purpose & Capability
Name/description describe extracting 32 fields from medical-insurance documents; the repository contains a small Python script that extracts text from PDF/DOCX/TXT and a detailed output-format spec. Declared dependencies (PyPDF2, python-docx) match the parser's needs. No unrelated credentials, binaries, or install steps are requested.
ℹ Instruction Scope
SKILL.md limits runtime behavior to: (1) run scripts/parse_document.py on user-supplied files or parse provided text, (2) map extracted text to the JSON schema in references/output-format.md. This stays within scope. Note: the README asserts the AI can '100% extract' Level 1 fields — that is an overconfident claim (extraction quality depends on document layout, OCR needs for scanned PDFs, ambiguous language, etc.). The skill does not handle OCR or images; it only extracts text content.
✓ Install Mechanism
No install spec provided (instruction-only), so nothing is downloaded or executed beyond the included parse_document.py. Dependencies are declared in SKILL.md but not automatically installed by the skill; missing libraries will cause the script to raise ImportError. No external URLs, archives, or unusual install locations are used.
✓ Credentials
The skill requires no environment variables, credentials, or config paths. The requested resources are proportional to its function (text parsing of user-provided documents).
✓ Persistence & Privilege
The skill does not request always:true or other elevated persistence. It contains no code that modifies other skills or system-wide configs; it simply reads input files and prints extracted text.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install insurance-policy-parser
  3. After installation, invoke the skill by name or use /insurance-policy-parser
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Extracts 32 structured fields from medical insurance policy documents in PDF, DOCX, or TXT formats, outputting standardized JSON. - Supports both core (14) and enhancement (18) fields as defined in the output format specification. - Implements automated data type conversion for amounts, proportions, enumerations, and booleans. - Provides a document parsing script for robust text extraction from files. - Ensures all Level 1 core fields are mandatory and accurately extracted; Level 2 enhancement fields allow nulls. - Output strictly follows predefined JSON formatting and field rules.
Metadata
Slug insurance-policy-parser
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 保险条款分析?

解析医疗险条款文档并提取32个结构化字段，含14个核心字段和18个增强字段，支持PDF/DOCX/TXT格式，输出标准JSON. It is an AI Agent Skill for Claude Code / OpenClaw, with 289 downloads so far.

How do I install 保险条款分析?

Run "/install insurance-policy-parser" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 保险条款分析 free?

Yes, 保险条款分析 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 保险条款分析 support?

保险条款分析 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 保险条款分析?

It is built and maintained by 马龙 (@long1973m); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments