← 返回 Skills 市场

智能照护排班

Name: 智能照护排班
Author: cnspica

作者 Sean zheng · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

180

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-care-scheduler

功能描述

通过对话即可完成养老机构护理排班，简单快捷

使用说明 (SKILL.md)

\r \r

智能照护排班\r

\r 通过对话就能完成排班，无需打开网页。\r \r

触发方式\r

\r 当用户说以下内容时，使用此 skill：\r

"帮我生成养老院排班表"\r
"创建护理排班"\r
"帮我排个班"\r
"生成排班表"\r \r

对话流程\r

\r 第1步：询问工作人员\r 请告诉我要排班的工作人员姓名，每行一个。\r \r 例如：张三、李四、王五、赵阿姨\r \r 第2步：确认参数\r

每人每周上几班？（默认5班）\r
排班周期：一周还是一个月？（默认一周）\r
从哪天开始？（默认下周周一）\r \r 第3步：生成排班\r 直接生成排班表，以表格形式展示，并询问是否需要导出CSV。\r \r

排班规则（自动应用）\r

不连续排班（连续上班后休息1天）\r
夜班后必须休息1天\r
每周班次不超过设定值\r
尽量公平分配\r \r

班次配置\r

\r 系统默认配置：\r

早班 07:00-15:00（需要2人）\r
中班 15:00-23:00（需要2人）\r
夜班 23:00-07:00（需要1人）\r \r

输出格式\r

\r 排班结果以 Markdown 表格形式展示，包含：日期、班次、时间、值班人员。\r \r

示例\r

\r 用户：帮我生成排班表\r \r 你：请告诉我工作人员姓名（每行一个）\r \r 用户：张护士、李护理员、王护工、赵阿姨、钱大姐、孙护士\r \r 你：好的，7人排班。一周还是一个月？每人每周几班？从哪天开始？\r \r 用户：一周，每人5班，从下周一开始\r \r 你：生成排班表...\r \r | 日期 | 班次 | 时间 | 值班人员 |\r |------|------|------|----------|\r | 3月17日周一 | 早班 | 07:00-15:00 | 张护士、李护理员 |\r | 3月17日周一 | 中班 | 15:00-23:00 | 王护工、赵阿姨 |\r | ... | ... | ... | ... |\r \r 需要导出CSV文件吗？\r

安全使用建议

The skill appears to do what it says: it generates schedules and can export CSVs. Before installing or using it, review the bundled assets/app.js generate() path to confirm whether it sends data to an external API when an API key is provided. If you will process real staff/personal data, prefer the local Python generator (scheduler.py), avoid entering any third‑party API keys, and run the code in a controlled environment so exported CSVs are stored where you expect. If you plan to supply an external model key, verify the exact endpoint and data sent (staff names and shift details are sensitive) and only use a trusted, privacy-compliant service.

功能分析

Type: OpenClaw Skill Name: ai-care-scheduler Version: 1.0.0 The skill bundle provides a legitimate tool for generating nursing schedules for elderly care facilities via both a web interface and AI agent instructions. The logic in `scheduler.py` and `assets/app.js` is consistent with the stated purpose, implementing standard scheduling constraints (e.g., rest after night shifts). While `assets/app.js` allows for an optional Aliyun API key to use AI for generation, it communicates directly with the official endpoint (dashscope.aliyuncs.com) and lacks any indicators of data exfiltration, malicious execution, or harmful prompt injection.

能力评估

✓ Purpose & Capability

Name/description (care scheduling) match the included Python and JS code: scheduler.py and generate.py implement local schedule generation and CSV export; assets implement a UI for entering staff and generating schedules. No unrelated credentials, binaries, or install steps are requested.

ℹ Instruction Scope

SKILL.md instructs a simple conversational flow to collect staff names and parameters and to output a Markdown table and offer CSV export. That stays within scope. The included code will create CSV files on disk if executed; SKILL.md does not explicitly document use of the bundled scripts or the client-side '通义千问 API Key' UI element seen in assets/app.js, which could allow the app to call an external model if implemented.

✓ Install Mechanism

No install spec or remote downloads; this is primarily code bundled with the skill (no package installs or archive downloads). This is lower risk than remote install mechanisms.

ℹ Credentials

The skill declares no required env vars or credentials (primaryEnv none). However, assets/app.js exposes an optional input labeled '通义千问 API Key' and a link to dashscope.console.aliyun.com; if the JS uses that key it could transmit staff names and schedule data to a third-party model service. The SKILL.md does not mention this optional external API. Do not provide API keys unless you trust the endpoint and have reviewed the client code path.

✓ Persistence & Privilege

always:false and no system-wide config changes. The Python code writes CSV files to the local working directory when exporting—normal for this function but be aware of filesystem writes. There is no indication the skill modifies other skills or requests elevated privileges.

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 ai-care-scheduler
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-care-scheduler 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

v1.0.0

智能照护排班 1.0.0 - 首个版本上线 - 支持通过自然语言对话快速生成养老机构护理排班表 - 自动询问工作人员名单、班次参数及起始日期 - 智能应用排班规则，确保公平、合理排班 - 支持早班、中班、夜班自动分配，内置默认班次需求 - 排班表结果以 Markdown 表格展示，并可导出为CSV

元数据

Slug ai-care-scheduler

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题