← Back to Skills Marketplace
daimingvip-a11y

中国法律合规AI技能包

by daimingvip-a11y · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
335
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install legal-compliance-bundle
Description
提供50个面向中国企业的AI法律合规自动化技能,涵盖合同审查、法律问答、劳动合规、知识产权及数据保护等领域。
README (SKILL.md)

中国法律合规AI技能包 (Legal Compliance Skill Bundle)

版本: 1.0.0 | 作者: 周田田 | 定价: ¥2,999/包(含50个技能+安全审计报告)

概述

本技能包为中国企业法务团队提供50个AI驱动的法律合规自动化技能,覆盖合同审查、法规查询、劳动合规、知识产权、数据保护等核心领域。

基于中国现行法律法规知识库,每个技能可独立运行或组合使用。

技能清单 (50 Skills)

合同管理 (10 Skills)

# 技能ID 名称 功能描述 状态
1 contract-review 合同审查 自动审查合同条款,标记风险点
2 contract-clause-suggest 条款建议 根据场景推荐标准条款
3 contract-compare 合同对比 对比两份合同的差异点
4 contract-extract 关键信息提取 从合同中提取甲乙方、金额、期限等
5 contract-template-gen 模板生成 根据需求生成合同模板
6 contract-risk-score 风险评分 给合同打风险分(0-100)
7 contract-amendment-gen 修订生成 生成合同修订建议文档
8 contract-expiry-monitor 到期监控 监控合同到期日并提醒
9 contract-signature-verify 签章验证 检查合同签署要素完整性
10 contract-nlp-search 智能搜索 自然语言搜索合同库

法律问答 (8 Skills)

# 技能ID 名称 功能描述 状态
11 legal-qa 法律问答 基于中国法律知识库的问答
12 case-law-search 判例检索 检索相关案例和判决
13 regulation-explain 法规解读 用通俗语言解释法律条文
14 legal-opinion-gen 法律意见书 自动生成法律意见书草稿
15 litigation-risk-assess 诉讼风险评估 评估案件胜诉概率和风险
16 statute-limitation-check 时效检查 检查诉讼时效是否过期
17 legal-news-monitor 法规动态监控 监控新法规/司法解释发布
18 legal-faq-builder FAQ构建器 自动生成常见法律FAQ

劳动合规 (8 Skills)

# 技能ID 名称 功能描述 状态
19 labor-contract-check 劳动合同审查 审查劳动合同合规性
20 social-insurance-calc 社保计算 计算社保公积金缴纳基数
21 overtime-compliance 加班合规 检查加班安排是否合规
22 termination-risk 解雇风险评估 评估解除劳动合同的风险
23 labor-dispute-guide 劳动争议指南 劳动仲裁/诉讼流程指引
24 employee-handbook-gen 员工手册生成 生成合规的员工手册
25 non-compete-review 竞业限制审查 审查竞业限制条款合理性
26 workplace-harassment-policy 反骚扰政策 生成职场反骚扰制度

知识产权 (6 Skills)

# 技能ID 名称 功能描述 状态
27 trademark-search 商标检索 检索商标注册情况
28 patent-draft-assist 专利辅助 辅助撰写专利申请文件
29 copyright-notice-gen 版权声明生成 生成版权声明/许可协议
30 ip-infringement-assess 侵权评估 评估知识产权侵权风险
31 trade-secret-policy 商业秘密保护 生成商业秘密保护制度
32 ip-licensing-template 许可协议模板 生成IP许可协议模板

数据合规 (8 Skills)

# 技能ID 名称 功能描述 状态
33 pipl-compliance-check PIPL合规检查 检查个人信息保护法合规性
34 privacy-policy-gen 隐私政策生成 生成App/网站隐私政策
35 data-classification 数据分类分级 数据资产分类分级评估
36 cross-border-assess 出境评估 数据出境安全评估辅助
37 consent-management 合规同意管理 设计用户同意流程
38 data-breach-response 数据泄露应急 生成数据泄露应急预案
39 dsar-handler 个人信息请求处理 处理用户个人信息查阅/删除请求
40 dpi-template 影响评估模板 生成数据保护影响评估模板

企业合规 (10 Skills)

# 技能ID 名称 功能描述 状态
41 aml-kyc-check 反洗钱/KYC 反洗钱合规检查清单
42 anti-bribery-policy 反贿赂制度 生成反商业贿赂制度
43 compliance-training-gen 合规培训生成 生成合规培训材料
44 regulatory-filing-assist 监管报送辅助 辅助监管报表填写
45 board-resolution-gen 决议生成 生成股东会/董事会决议模板
46 company-policy-review 制度审查 审查公司内部制度合规性
47 external-counsel-brief 外部律师简报 生成给外部律师的案情简报
48 compliance-risk-matrix 合规风险矩阵 生成企业合规风险评估矩阵
49 annual-compliance-report 年度合规报告 生成年度合规工作汇报
50 compliance-audit-checklist 合规审计清单 生成内部合规审计检查表

安全审计报告

每个技能包附带安全审计报告(SkillFortify格式):

  • 形式化验证: F1=96.95%,零误报
  • 供应链安全: 不含恶意代码、不依赖可疑第三方包
  • 数据安全: 所有数据本地处理,不外传

快速开始

# 安装技能包
clawhub install legal-compliance-bundle

# 配置
cp config/legal-config.yaml.template config/legal-config.yaml
# 编辑 config/legal-config.yaml 填入你的企业信息

# 使用单个技能
openclaw run contract-review --input contract.pdf

# 使用技能组合
openclaw run compliance-audit-checklist --scope "data+labor+ip"

依赖

  • OpenClaw >= 0.8.0
  • Python >= 3.10
  • DeepSeek API Key (可选,用于高级法律问答)

定价

套餐 价格 包含
基础版 ¥999 10个核心技能(合同+法律问答)
标准版 ¥1,999 30个技能(含劳动+知识产权)
完整版 ¥2,999 全部50个技能+安全审计报告
企业定制 ¥5,000+ 定制技能+专属知识库+部署支持
Usage Guidance
This bundle appears to implement what it advertises and runs primarily with local Python scripts, but note the package has an unknown source (no homepage) and claims an external 'DeepSeek API Key' option. Before installing: 1) Review the included config/legal-config.yaml.template and any omitted files for sensitive data sinks; 2) Do not enable or populate external API keys (DeepSeek or similar) until you verify the endpoint and privacy policy; 3) Run the package in an isolated/test environment first (do not point it at production data) and inspect network activity if you enable optional features; 4) Verify the claimed security audit and supply-chain statements with the vendor or independent review; 5) If you will purchase or deploy this in production, consider having legal/compliance or security engineers audit the remaining omitted files and the config handling.
Capability Analysis
Type: OpenClaw Skill Name: legal-compliance-bundle Version: 1.0.0 The Legal Compliance Skill Bundle is a legitimate collection of 50 automation tools for Chinese legal and compliance tasks, including contract review, labor law analysis, and data protection (PIPL) checks. The scripts (e.g., contract_review.py, labor_contract_check.py) primarily utilize regular expressions and local knowledge bases to identify risks and generate reports or templates. The DeepSeek API integration in legal_qa.py is a standard feature for advanced Q&A and requires a user-provided key. No evidence of data exfiltration, malicious execution, or prompt injection was found; the high-risk clauses in knowledge/sample_contract.txt are clearly intended as test cases for the review scripts.
Capability Assessment
Purpose & Capability
The 50 included Python scripts implement the contract, labor, IP, data, and enterprise-compliance features described in SKILL.md and README (contract review, extraction, templates, audits, risk matrices, etc.). No obvious requests (env vars, binaries, system paths) are disproportionate to the stated purpose.
Instruction Scope
SKILL.md gives reasonable local usage instructions (install via clawhub, copy a config template, run specific skills). It also mentions an optional 'DeepSeek API Key' for advanced legal QA; the core instructions and many scripts operate locally, but enabling an optional external API would transmit queries externally — that behavior is optional but not fully documented in requires.env (i.e., optional external endpoints are not declared).
Install Mechanism
There is no install spec and the package is instruction-plus-script based; the files are plain Python scripts (no network download/install steps shown). This is lower-risk from an automatic install perspective, though manual installation via clawhub/openclaw may execute scripts on the host.
Credentials
The skill declares no required environment variables or credentials, which matches the largely local processing scripts. However SKILL.md advertises an optional third‑party DeepSeek API key (not declared as required) and asks users to populate a config/legal-config.yaml — that config may contain enterprise data. The optional API and config file are the main vectors that could expose sensitive data if enabled or misconfigured.
Persistence & Privilege
The package does not request always:true or other elevated persistent privileges; it is user-invocable and can be run interactively. Nothing in the manifest indicates modification of other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install legal-compliance-bundle
  3. After installation, invoke the skill by name or use /legal-compliance-bundle
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: 50 legal compliance skills covering contracts, labor, IP, data privacy, and corporate compliance
Metadata
Slug legal-compliance-bundle
Version 1.0.0
License MIT-0
All-time Installs 2
Active Installs 2
Total Versions 1
Frequently Asked Questions

What is 中国法律合规AI技能包?

提供50个面向中国企业的AI法律合规自动化技能,涵盖合同审查、法律问答、劳动合规、知识产权及数据保护等领域。 It is an AI Agent Skill for Claude Code / OpenClaw, with 335 downloads so far.

How do I install 中国法律合规AI技能包?

Run "/install legal-compliance-bundle" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 中国法律合规AI技能包 free?

Yes, 中国法律合规AI技能包 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 中国法律合规AI技能包 support?

中国法律合规AI技能包 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 中国法律合规AI技能包?

It is built and maintained by daimingvip-a11y (@daimingvip-a11y); the current version is v1.0.0.

💬 Comments