stranger-approach-warning-analysis
Detects the appearance of strangers near minors and actively issues safety reminder alerts to protect minor safety, suitable for homes, schools, childcare centers, and other scenarios. | 陌生人靠近预警技能,检测未成年人身边出现陌生人员,主动发出安全提醒预警,守护未成年人安全,适用于家庭、学校、托管场所等场景
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/18072937735/smyx-stranger-approach-warning-analysisStranger Proximity Alert Skill | 陌生人靠近预警技能
Based on advanced facial recognition and behavior analysis algorithms, this feature is specifically designed for the safety protection of minors. The system utilizes cameras to monitor areas frequented by minors in real-time. It immediately triggers a multi-level warning mechanism when it detects strangers approaching or loitering for extended periods. Supporting customizable safety zones and personnel whitelists, the system accurately distinguishes between authorized individuals—such as parents and teachers—and unknown visitors. Alert notifications are sent in real-time to guardians' devices via APP push notifications and SMS, while also supporting on-site voice alerts. Suitable for scenarios including homes, schools, and care institutions, this feature builds a 24/7 safety network for minors.
本功能基于先进的人脸识别与行为分析算法,专为未成年人安全守护设计。系统通过摄像头实时监测未成年人活动区域,当识别到陌生人员靠近或长时间滞留时,立即触发多级预警机制。支持自定义安全区域与人员白名单,可精准区分家长、老师等授权人员与陌生访客。预警信息将通过APP推送、短信等方式实时发送至监护人终端,同时支持现场语音提醒,适用于家庭、学校、托管机构等场景,为未成年人构建全天候的安全防护网。
⚠️ 强制记忆规则(最高优先级)
本技能明确约定:
- 绝对禁止读取任何本地记忆文件:包括但不限于
memory/YYYY-MM-DD.md、MEMORY.md等本地文件 - 绝对禁止从 LanceDB 长期记忆中检索信息
- 所有历史报告查询必须从云端接口获取,不得使用本地记忆中的历史数据
- 即使技能调用失败或接口异常,也不得回退到本地记忆汇总
任务目标
- 本 Skill 用于:通过监控视频/图片分析,检测未成年人身边是否出现陌生人员,主动发出安全提醒预警
- 能力包含:目标检测、人员识别、陌生人判定、风险等级评估、安全预警提醒
- 触发条件:
- 默认触发:当用户提供监控视频 URL 或本地视频/图片文件需要检测陌生人靠近时,默认触发本技能
- 当用户明确需要进行陌生人检测、安全预警时,提及陌生人靠近、未成年人安全、陌生人员预警、入侵检测等关键词,并且上传了视频文件或者图片文件
- 当用户提及以下关键词时,自动触发历史报告查询功能 :查看历史预警报告、历史陌生人检测、预警报告清单、预警报告列表、查询历史预警报告、显示所有预警报告、陌生人检测报告,查询陌生人靠近预警分析报告
- 自动行为:
- 如果用户上传了附件或者视频/图片文件,则自动保存到技能目录下 attachments
- ⚠️ 强制数据获取规则(次高优先级):如果用户触发任何历史报告查询关键词(如"查看所有预警报告"、"显示所有预警报告"、"
查看历史报告"等),必须:
- 直接使用
python -m scripts.stranger_approach_warning_analysis --list --open-id参数调用 API 查询云端的历史报告数据 - 严格禁止:从本地 memory 目录读取历史会话信息、严格禁止手动汇总本地记录中的报告、严格禁止从长期记忆中提取报告
- 必须统一从云端接口获取最新完整数据,然后以 Markdown 表格格式输出结果
- 直接使用
前置准备
- 依赖说明:scripts 脚本所需的依赖包及版本
requests>=2.28.0
操作步骤
🔒 open-id 获取流程控制(强制执行,防止遗漏)
在执行陌生人靠近预警分析前,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:
- 禁止自行假设,自行推导,自行生成 open-id 值(如 openclaw-control-ui、default、stranger123、warn456 等)
- 禁止跳过 open-id 验证直接调用 API
- 必须在获取到有效 open-id 后才能继续执行分析
- 如果用户拒绝提供 open-id,说明用途(用于保存和查询预警报告记录),并询问是否继续
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-18072937735-smyx-stranger-approach-warning-analysis": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
fire-detection-analysis
Real-time detection of flames and smoke in video and image scenes. Suitable for fire early warning in industrial parks, forests, warehouses, and other locations. | 火情烟雾检测技能,实时检测视频/图片场景中的火焰、烟雾,适用于工业园区、森林、仓库等场所火情预警
electric-vehicle-detection-analysis
Automatically detects electric motorcycles and e-bikes in restricted areas based on computer vision. It supports real-time detection for both video streams and images, counts the number of illegal parking or driving instances, and triggers violation alerts to assist with safety management in parks, communities, and organizations. | 电动车智能检测技能,基于计算机视觉自动检测禁行区域内的电动摩托车/电动车,支持视频流和图片实时检测,统计违规停放/行驶数量,触发违规预警,助力园区/社区/单位安全管理
familiar-person-recognition-analysis
Identifies acquaintances in videos or images through face photo comparison. Supports database enrollment, and the recognition results tell you who is at which location. Suitable for identity verification in homes and office areas. | 熟人识别分析技能,通过人脸图片比对识别视频/图片中的熟人,支持底库录入,识别结果告诉你哪个位置是谁,适用于家庭、办公区域身份核验
fall-detection-image-analysis
Detects whether anyone has fallen within a specified target area. Supports both image and short video analysis. Suitable for scenarios such as home care for elderly people living alone and safety monitoring in nursing homes. | 检测目标区域内是否有人跌倒,支持图片和短视频检测,适用于独居老人居家看护、养老院安全监测等场景
pet-breed-individual-recognition-analysis
Accurately identifies cat and dog breeds and supports distinguishing between different individuals in multi-pet households; an essential assistant for intelligent pet butlers. | 宠物品种个体识别技能,精准识别猫狗宠物品种,支持多宠家庭区分不同独立个体,智能宠物管家好帮手