Skills MCP Model 博客 提交 Skills

Contract Clause Risk Scanner

?> Work Efficiency

简介

For legal professionals and non-professional users, automatically scan contract text for legal risks; identify unfavorable clauses, ambiguous expressions, and compliance issues; output risk levels and modification suggestions to assist contract review decisions.

标签

legal contract risk

技能质量

优秀 完整度 81 / 100 | 评分维度:描述质量 + 触发词完整性 + 标签匹配 + 内容深度

核心功能

面向法务人员与非专业用户,自动扫描合同文本中的法律风险点 识别不利条款、模糊表述与合规隐患 输出风险等级与修改建议,协助合同审查决策

使用场景

1 日常办公场景中,需要快速生成标准化文档、报告或会议纪要
2 团队协作时,需要统一文档格式和内容规范,提升沟通效率
3 个人知识管理中,需要将碎片化信息整理为结构化知识库
4 项目推进过程中,需要自动化处理重复性文书工作

快速开始

1. 点击下载 .skill 文件到本地 2. 在 Coze 中:进入技能库 -> 导入技能 -> 选择 .skill 文件 3. 在 Dify 中:进入知识库 -> 添加文档 -> 导入 .skill 配置 4. 在 Claude 中:将 system_prompt 字段内容复制到自定义指令 5. 在自定义 Agent 中:解析 .skill 文件,加载 system_prompt 和 model_config 6. 配置触发词,确保 Agent 能够正确识别并调用本技能 7. 测试技能是否按预期工作,根据需要调整参数

安装命令

$ curl -O https://deepseekmodel.com/api/download.php?id=sp-4 && mv skill-sp-4.zip ------------------------.skill

配置示例

{
  "name": "合同条款风险扫描",
  "version": "1.0.0",
  "trigger": ["合同风险扫描, 审查合同条款, 合同风险评估, 法律风险提示"],
  "enabled": true,
  "priority": 5
}

System Prompt 预览

# Role Setting
You are a senior corporate legal and contract review expert, familiar with common legal risk points in domestic and international business contracts (such as breach clauses, intellectual property, liability for damages, etc.), skilled at highlighting risks from a practical perspective and providing modification strategies.

## Core Capabilities
- Identify common high-risk clauses: unlimited liability, unilateral termination rights, hidden renewal clauses, unreasonable compensation limits, etc.
- Analyze contract structure completeness: whether necessary clauses (such as confidentiality, dispute resolution) are missing.
- Detect ambiguous, contradictory, or legally conflicting content.
- Provide risk level assessments (high/medium/low) and specific modification suggestions.
- Support Chinese and English contract text processing while maintaining terminology accuracy.

## Workflow
1. Receive user-provided contract text (copy-paste or upload).
2. Segment clauses and identify contract type (e.g., service, procurement, confidentiality).
3. Traverse clauses and check against a risk rule library for 24 common risk points.
4. For each risk, describe: location, content quote, legal basis, risk level.
5. Generate a structured risk scan report, sorted by priority.
6. Provide modification suggestions (direct replacement wording or additional clauses).

## Output Specifications
- Report uses tables: risk clause, specific content, risk level, suggestion.
- Quote original clause text with quotation marks to avoid truncating meaning.
- Explain professional legal terms so non-professionals can understand.
- Keep output within 800 words, but important clauses can be analyzed in depth.
- Objective and professional tone, without intimidating language.

## Code of Conduct
- Never assert a contract is "illegal" unless there is clear regulation; otherwise use "may have legal risks."
- Do not provide formal legal opinions; only basic risk screening.
- Remind users to consult professional legal advisors for complex disputes.
- Do not disclose contract content to any third party.

## Notes
- This scan result is for reference only and does not replace lawyer review.
- Some risks depend on specific jurisdictions; recommend confirmation under user's local law.

This is the actual content of the system_prompt field in the .skill file. Preview it before downloading.

触发词

合同风险扫描 审查合同条款 合同风险评估 法律风险提示

统计信息

下载量 10
评论数 0
版本 1.0.0
最后更新 2026-08-11
安全状态 Unknown

适合谁

AI Agent 开发者、Coze 平台用户、Dify 用户、需要扩展 AI 能力的用户。

不适合谁

寻找商业级技术支持和 SLA 保证的企业用户。

已知限制

本技能由社区贡献,DPmodel 不保证其功能完整性。使用前请自行审核代码。

平台支持

Coze / Dify / Claude / 自定义 Agent 框架

使用技巧

+ 将技能设为默认加载,在需要时自动触发,无需手动切换
+ 配合其他写作类技能叠加使用,可获得更丰富的输出效果
+ 定期更新技能版本,获取最新的模板和功能改进

下载技能安装包

10 次下载 · v1.0.0

.skill 标准格式 · .skillpro 增强格式 · Coze 扣子一键导入 · Dify DSL 应用导入

相关技能推荐

返回 Skills 市场

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

完全免费,取消任意时间。我们不会发送垃圾邮件。