← 返回 Skills 市场
police-NERRE
作者
Andy020326
· GitHub ↗
· v1.0.2
· MIT-0
129
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install police-nerre-test
功能描述
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
安全使用建议
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.
功能分析
Type: OpenClaw Skill
Name: police-nerre-test
Version: 1.0.2
The skill bundle is a specialized NLP tool designed for extracting entities and relationships from police report text into a structured JSON format. Analysis of SKILL.md and _meta.json reveals no executable code, external network requests, or malicious prompt injection attempts; the instructions are strictly focused on data formatting and extraction logic consistent with the stated purpose.
能力评估
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.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install police-nerre-test - 安装完成后，直接呼叫该 Skill 的名称或使用
/police-nerre-test触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
- Removed example data and extraction script files: examples/sample.json, scripts/extract.py.
- Updated skill name to "police-nerre-test" and version to 1.0.3.
- Expanded and revised schema: added new entity types (如昵称、外貌、涉案物品、危险物品、银行卡号、开户行、车牌号).
- Expanded and clarified relationship types; now includes多种亲属和所有权/纠纷关系类型.
- Enforced stricter output constraints: only strict JSON output allowed, no Markdown, explanations, or extra text.
- Output JSON structure and field order are fixed and must be preserved even if some entries are empty.
v1.0.1
- Added example data file: examples/sample.json
- Added extraction script: scripts/extract.py
v1.0.0
- Initial release of police-entity-extractor skill for extracting entities and relationships from police incident texts in JSON format.
- Supports 8 types of entities (姓名, 身份证号, 手机号, 地理位置, 事发地, 组织名称, 违法犯罪行为, 危险行为).
- Extracts 8 types of relationships, including 归属, 纠纷关系（人人）, 加害关系, 存在行为, 雇佣关系, 夫妻关系, and直系亲属关系.
- Provides strict extraction rules for each entity and relationship type.
- Outputs results in a standardized JSON structure.
元数据
常见问题
police-NERRE 是什么？
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 129 次。
如何安装 police-NERRE？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install police-nerre-test」即可一键安装，无需额外配置。
police-NERRE 是免费的吗？
是的，police-NERRE 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
police-NERRE 支持哪些平台？
police-NERRE 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 police-NERRE？
由 Andy020326（@andy020326）开发并维护，当前版本 v1.0.2。
推荐 Skills