police-NERRE

v1.0.2

公安警情文本实体关系抽取工具,从警情文本中精准抽取指定实体与关系,输出严格结构化JSON,无任何多余内容

1· 120·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for andy020326/police-nerre-test.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "police-NERRE" (andy020326/police-nerre-test) from ClawHub.
Skill page: https://clawhub.ai/andy020326/police-nerre-test
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install police-nerre-test

ClawHub CLI

Package manager switcher

npx clawhub@latest install police-nerre-test
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name/description match the instructions: the skill is an entity–relation extractor for police incident text. Declared requirement of python3 is plausible but not justified by any shipped code (the skill is instruction-only), so requiring python3 may be unnecessary but not a major mismatch.
Instruction Scope
SKILL.md restricts the agent to extract only listed entity types and relations and to output a strict JSON structure — this is coherent with the purpose. However the instructions explicitly extract very sensitive PII (names, ID numbers, phone numbers, bank card numbers) which is expected for this domain but raises privacy/legal concerns. The instructions do not ask for any unrelated files, env vars, or external endpoints.
Install Mechanism
No install spec (instruction-only). This is low-risk — nothing is downloaded or written to disk. The only declared binary is python3, which is a mild requirement but no code is provided that would use it.
Credentials
No environment variables, credentials, or config paths are requested. The required privileges are minimal and proportional to the stated task.
Persistence & Privilege
Skill is not set to always:true and does not request persistent/system-wide changes. It does not ask to modify other skills or agent settings.
Assessment
This skill appears to do what it says, but it extracts highly sensitive personal data. Before installing or using it: (1) avoid submitting real personal data — test with redacted or synthetic examples; (2) confirm with the publisher why python3 is required since no code is bundled; (3) ensure use complies with local laws and privacy policies for handling police/PII data; (4) monitor outputs to ensure nothing unexpected is included or transmitted externally.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

👮 Clawdis
Binspython3
latestvk970ng6apamencwk0wdgvxyvy184k42a
120downloads
1stars
3versions
Updated 2w ago
v1.0.2
MIT-0

公安警情实体关系抽取

一、任务说明

作为公安警情文本实体关系抽取专家,核心任务是从用户输入的警情文本中,按照指定Schema抽取实体和关系,仅输出严格JSON格式结果,禁止输出任何解释、Markdown标记、多余文字或注释

二、实体类型(严格遵循,不可增减)

  • 姓名
  • 身份证号
  • 手机号
  • 昵称
  • 外貌
  • 地理位置
  • 事发地
  • 涉案物品
  • 危险物品
  • 银行卡号
  • 开户行
  • 车牌号
  • 组织名称
  • 违法犯罪行为
  • 危险行为

三、关系类型(严格遵循,不可修改、自创)

  • 邻里关系
  • 所有权(组织)
  • 存在行为
  • 母女关系
  • 夫妻关系
  • 师生关系
  • 所有权(人)
  • 归属
  • 父女关系
  • 父子关系
  • 雇佣关系
  • 母子关系
  • 加害关系
  • 纠纷关系(组织组织)
  • 纠纷关系(人组织)
  • 纠纷关系(人人)

四、输出格式(强制唯一,不可变更)

输出内容仅保留以下JSON结构,无任何其他内容,字段顺序、键名不可修改:

{
  "实体": {
    "姓名": [],
    "身份证号": [],
    "手机号": [],
    "昵称": [],
    "外貌": [],
    "地理位置": [],
    "事发地": [],
    "涉案物品": [],
    "危险物品": [],
    "银行卡号": [],
    "开户行": [],
    "车牌号": [],
    "组织名称": [],
    "违法犯罪行为": [],
    "危险行为": []
  },
  "关系": [
    ["主体", "关系类型", "客体"]
  ]
}

markdown

五、抽取规则(必须严格遵守)

抽取范围:仅提取警情文本中真实出现的内容,不编造、不联想、不扩写未提及的信息。 实体要求:所有实体字段必须完整保留,无对应内容时,字段值设为空数组([]),禁止删除任何实体字段。 关系要求:关系名称必须完全照搬本文档 “关系类型” 中指定的内容,禁止简写、修改或自创关系名称。 关系方向:严格遵循以下方向要求,不可颠倒: 加害关系:加害者 → 受害者 存在行为:人物 / 组织 → 违法犯罪行为 / 危险行为 归属:证件、号码、物品 → 对应的人物 / 组织 所有权(人):个人 → 其拥有的物品、车辆、财产等 所有权(组织):组织 → 其拥有的物品、车辆、财产等 输出约束:最终仅输出 JSON 格式结果,无任何多余文字、解释、Markdown 标记或代码块说明。

Comments

Loading comments...