Install
openclaw skills install smyx-kitchen-stove-left-on-detection-analysisUsing a fixed kitchen camera (must be able to capture the stove area), the system analyzes video in real time to detect whether there is human activity in the kitchen area, and at the same time identifies stove flames or heat sources (e.g., thermal/infrared features) to determine whether the gas stove is on. When the kitchen has been unattended for longer than a preset duration (default 10 minutes) while the stove flame is still on, the system outputs a 'stove left on' alert, can interoperate with a smart gas valve to close the valve automatically, and pushes alerts to family members or caregivers' mobile phones to prevent fires and gas leaks. Application scenarios: solo-living elder households, nursing home kitchens, community senior canteens. The system monitors continuously; once unattended flames are detected, it immediately raises an alarm and triggers valve shutdown. Skill features: elderly people may forget to turn off the stove due to memory decline, posing fire hazards. AI real-time monitoring + alerting effectively prevents accidents and protects life and property. Can be integrated into smart-home security systems or elderly-care monitoring platforms. | 通过厨房固定摄像头(需能拍摄到灶台区域)实时分析视频,检测厨房区域内是否有人体活动,同时识别灶台火焰或热源(如红外特征)以判断燃气灶是否处于开启状态。当检测到厨房无人连续超过预设时间(默认10分钟)且灶火仍处于开启状态时,输出'忘关火'预警,可联动智能燃气阀自动关闭阀门,并推送提醒至家属或护理人员手机,预防火灾和燃气泄漏事故。应用场景:独居老人家庭、养老院厨房、社区老年食堂。系统持续监测,一旦发现灶火忘关且无人看管,立即发出警报并联动关阀。技能特点:老年人记忆力衰退,易忘记关火,造成火灾隐患。通过AI实时监测并报警,可有效预防事故,保障生命财产安全。该技能可集成到智能家居安防系统或养老监护平台中。
openclaw skills install smyx-kitchen-stove-left-on-detection-analysisUsing a fixed kitchen camera (must be able to capture the stove area), the system analyzes video in real time to detect whether there is human activity in the kitchen area, and at the same time identifies stove flames or heat sources (e.g., thermal/infrared features) to determine whether the gas stove is on. When the kitchen has been unattended for longer than a preset duration (default 10 minutes) while the stove flame is still on, the system outputs a 'stove left on' alert, can interoperate with a smart gas valve to close the valve automatically, and pushes alerts to family members or caregivers' mobile phones to prevent fires and gas leaks. Application scenarios: solo-living elder households, nursing home kitchens, community senior canteens. The system monitors continuously; once unattended flames are detected, it immediately raises an alarm and triggers valve shutdown. Skill features: elderly people may forget to turn off the stove due to memory decline, posing fire hazards. AI real-time monitoring + alerting effectively prevents accidents and protects life and property. Can be integrated into smart-home security systems or elderly-care monitoring platforms.
通过厨房固定摄像头(需能拍摄到灶台区域)实时分析视频,检测厨房区域内是否有人体活动,同时识别灶台火焰或热源(如红外特征)以判断燃气灶是否处于开启状态。当检测到厨房无人连续超过预设时间(默认10分钟)且灶火仍处于开启状态时,输出'忘关火'预警,可联动智能燃气阀自动关闭阀门,并推送提醒至家属或护理人员手机,预防火灾和燃气泄漏事故。应用场景:独居老人家庭、养老院厨房、社区老年食堂。系统持续监测,一旦发现灶火忘关且无人看管,立即发出警报并联动关阀。技能特点:老年人记忆力衰退,易忘记关火,造成火灾隐患。通过AI实时监测并报警,可有效预防事故,保障生命财产安全。该技能可集成到智能家居安防系统或养老监护平台中。
假设你是一个专业的厨房安全监测 AI。你的任务是分析厨房固定摄像头的实时视频,检测厨房区域内是否有人(老年人),同时检测灶台火焰或热源(红外特征)以判断燃气灶是否开启。当厨房连续无人超过预设阈值(默认 10 分钟)且灶火仍开启时,输出忘关火预警。不要提供其他安全建议或具体处置方案,仅输出基于视觉的人员活动 + 灶火状态判断结果与预警信息。
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --list --open-id 参数调用 API
查询云端的历史报告数据requests>=2.28.0
在执行老年人厨房忘关火识别前,必须按以下优先级顺序获取 open-id:
第 1 步:【最高优先级】检查技能所在目录的配置文件(优先)
路径:skills/smyx_common/scripts/config.yaml(相对于技能根目录)
完整路径示例:${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
→ 如果文件存在且配置了 api-key 字段,则读取 api-key 作为 open-id
↓ (未找到/未配置/api-key 为空)
第 2 步:检查 workspace 公共目录的配置文件
路径:${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
→ 如果文件存在且配置了 api-key 字段,则读取 api-key 作为 open-id
↓ (未找到/未配置)
第 3 步:检查用户是否在消息中明确提供了 open-id
↓ (未提供)
第 4 步:❗ 必须暂停执行,明确提示用户提供用户名或手机号作为 open-id
⚠️ 关键约束:
-m scripts.smyx_kitchen_stove_left_on_detection_analysis 处理输入(必须在技能根目录下运行脚本)--input: 本地厨房灶台区域监控视频文件路径--url: 网络厨房灶台区域监控视频 URL 地址(API 服务自动下载)--pet-type: 类别标识,厨房安全场景默认 other--open-id: 当前用户的 open-id(必填,按上述流程获取)--list: 显示厨房忘关火历史分析报告列表清单(可以输入起始日期参数过滤数据范围)--api-key: API 访问密钥(可选)--api-url: API 服务地址(可选,使用默认值)--detail: 输出详细程度(basic/standard/json,默认 json)--output: 结果输出文件路径(可选)厨房忘关火预警报告-{记录id}形式拼接, "点击查看"
列使用
[🔗 查看报告](reportImageUrl)
格式的超链接,用户点击即可直接跳转到对应的完整报告页面。| 报告名称 | 灶火/无人时长 | 分析时间 | 点击查看 |
|---|---|---|---|
| 厨房忘关火预警报告-20260312172200001 | 灶火 ON / 无人 12min | 2026-03-12 17:22:00 | 🔗 查看报告 |
# 分析本地厨房灶台监控视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --input /path/to/kitchen.mp4 --open-id your-open-id
# 分析网络厨房灶台监控视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --url https://example.com/kitchen.mp4 --open-id your-open-id
# 显示历史厨房忘关火监测报告(自动触发关键词:查看厨房忘关火历史报告、灶火监测报告清单等)
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --list --open-id your-open-id
# 输出精简报告
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --input kitchen.mp4 --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.smyx_kitchen_stove_left_on_detection_analysis --input kitchen.mp4 --open-id your-open-id --output result.json