Install
openclaw skills install smyx-rehab-motivation-encouragement-analysisThrough fixed cameras in rehabilitation centers or home rehab areas, the system analyzes video of patients during rehabilitation training to detect frustration / giving-up tendency behaviors: sighing (rapid chest-abdomen rise-fall with exhalation), training interruption (actively stopping before reaching preset reps or duration), head-down silence (head lowered, avoiding eye contact, long-term silence), sluggish or perfunctory movements (joint range of motion noticeably smaller than the early training phase), and long-term lack of progress (stagnation or decline of the same training item over consecutive days). When such behaviors are detected, the system automatically plays personalized encouragement audio (e.g. 'You are doing great, one more set!') and at the same time shows progress-comparison data against yesterday (or the most recent session) via screen or voice (e.g. 'You did 2 more leg lifts today than yesterday'). This skill aims to improve patient motivation and adherence and reduce frustration-induced rehab discontinuation. Application scenarios: physical therapy rehabilitation centers, home rehab areas, occupational therapy rooms. The system monitors in real time and provides positive reinforcement promptly when the patient shows giving-up tendency. Skill features: rehab coaches cannot accompany patients 24 hours a day; standard rehab equipment lacks emotional motivation; this skill leverages AI vision (and optional audio) to actively identify frustration and provide personalized motivation, filling the gap in intelligent rehab psychological support. | 通过康复中心或家庭康复区的固定摄像头,分析患者在进行康复训练时的视频,检测沮丧/放弃倾向行为:叹气(胸腹快速起伏伴呼气声)、中断训练(在未达到预设次数或时间前主动停止动作)、低头不语(头部低垂,避免眼神接触,长时间无言语)、动作迟缓或敷衍(关节活动范围明显小于前期),以及长时间无进展(连续多日同一训练项目的表现停滞或下降)。当检测到上述行为时,系统自动播放个性化鼓励语音(如'您已经很棒了,再坚持一次!'),并同时通过屏幕或语音展示与昨日(或最近一次)的进步对比数据(如'您今天比昨天多做 2 次抬腿')。该技能旨在提升康复患者的积极性和依从性,减少因沮丧导致的康复中断。应用场景:物理治疗康复中心、家庭康复区、作业治疗室。系统实时监测,在患者出现放弃倾向时及时给予正向激励。技能特点:康复教练不可 24 小时陪伴;普通康复设备无情绪激励;本技能利用 AI 视觉(及可选音频)主动识别沮丧情绪并提供个性化激励,填补智能康复心理支持空白。
openclaw skills install smyx-rehab-motivation-encouragement-analysisThrough fixed cameras in rehabilitation centers or home rehab areas, the system analyzes video of patients during rehabilitation training to detect frustration / giving-up tendency behaviors: sighing (rapid chest-abdomen rise-fall with exhalation), training interruption (actively stopping before reaching preset reps or duration), head-down silence (head lowered, avoiding eye contact, long-term silence), sluggish or perfunctory movements (joint range of motion noticeably smaller than the early training phase), and long-term lack of progress (stagnation or decline of the same training item over consecutive days). When such behaviors are detected, the system automatically plays personalized encouragement audio (e.g. 'You are doing great, one more set!') and at the same time shows progress-comparison data against yesterday (or the most recent session) via screen or voice (e.g. 'You did 2 more leg lifts today than yesterday'). This skill aims to improve patient motivation and adherence and reduce frustration-induced rehab discontinuation. Application scenarios: physical therapy rehabilitation centers, home rehab areas, occupational therapy rooms. The system monitors in real time and provides positive reinforcement promptly when the patient shows giving-up tendency. Skill features: rehab coaches cannot accompany patients 24 hours a day; standard rehab equipment lacks emotional motivation; this skill leverages AI vision (and optional audio) to actively identify frustration and provide personalized motivation, filling the gap in intelligent rehab psychological support.
通过康复中心或家庭康复区的固定摄像头,分析患者在进行康复训练时的视频,检测沮丧/放弃倾向行为:叹气(胸腹快速起伏伴呼气声)、中断训练(在未达到预设次数或时间前主动停止动作)、低头不语(头部低垂,避免眼神接触,长时间无言语)、动作迟缓或敷衍(关节活动范围明显小于前期),以及长时间无进展(连续多日同一训练项目的表现停滞或下降)。当检测到上述行为时,系统自动播放个性化鼓励语音(如'您已经很棒了,再坚持一次!'),并同时通过屏幕或语音展示与昨日(或最近一次)的进步对比数据(如'您今天比昨天多做 2 次抬腿')。该技能旨在提升康复患者的积极性和依从性,减少因沮丧导致的康复中断。应用场景:物理治疗康复中心、家庭康复区、作业治疗室。系统实时监测,在患者出现放弃倾向时及时给予正向激励。技能特点:康复教练不可 24 小时陪伴;普通康复设备无情绪激励;本技能利用 AI 视觉(及可选音频)主动识别沮丧情绪并提供个性化激励,填补智能康复心理支持空白。
假设你是一个专业的康复心理支持 AI。你的任务是分析康复训练区域固定摄像头(可选麦克风)的实时音视频,检测患者沮丧或放弃倾向行为:叹气(胸腹快速隆起-收缩伴呼气节律)、中断训练(预设训练时段内提前停止动作)、低头不语(头部低垂 + 面部无表情交流 + 言语沉默)、动作迟缓或敷衍(关节活动幅度比训练初期显著缩小、节律乱、速度慢)、连续多日无进展(当日 vs 近 3 日训练完成度趋势)。综合评估沮丧等级,按 4 级激励策略递进:Level 1 智能音箱温和鼓励语 → Level 2 屏幕/语音展示进步对比数据(基于真实历史记录) → Level 3 康复师 APP 提醒介入 → Level 4 紧急推送康复师 + 家属并建议切换轻松项目/休息。3 分钟未改善自动升级。激励语必须个性化、具体、肯定(基于真实进步数据),禁用"加油坚持就是胜利 / 别人都能你怎么不行 / 你这样不行"等压力型或对比型话术。严禁伪造或夸大进步数据,严禁 AI 克隆家属/康复师声音,严禁越权调整训练强度。不提供任何医疗诊断,仅输出基于视觉的行为评估和激励建议。
python -m scripts.smyx_rehab_motivation_encouragement_analysis --list --open-id 参数调用 API
查询云端的历史报告数据requests>=2.28.0
在执行康复患者沮丧/放弃倾向激励前,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_rehab_motivation_encouragement_analysis 处理输入(必须在技能根目录下运行脚本)--input: 本地康复中心/家庭康复区固定摄像头训练时段视频文件路径--url: 网络康复中心/家庭康复区固定摄像头训练时段视频 URL 地址(API 服务自动下载)--pet-type: 类别标识,康复激励场景默认 other--open-id: 当前用户的 open-id(必填,患者本人或家属/康复师授权)--list: 显示康复患者沮丧/放弃倾向激励历史记录清单--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)康复激励-{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 | 场景/等级/已执行激励动作 | 分析时间 | 点击查看 |
|---|---|---|---|
| 康复激励-20260519143200001 | rehab_motivation_perfunctory / strong / 鼓励语+进步对比+康复师 APP 推送 | 2026-05-19 14:32:00 | 🔗 查看报告 |
# 分析本地康复训练视频(以下只是示例,禁止直接使用 openclaw-control-ui 作为 open-id)
python -m scripts.smyx_rehab_motivation_encouragement_analysis --input /path/to/rehab_session.mp4 --open-id your-open-id
# 分析网络康复训练视频/实时流(以下只是示例,禁止直接使用 openclaw-control-ui 作为 open-id)
python -m scripts.smyx_rehab_motivation_encouragement_analysis --url https://example.com/rehab_session.mp4 --open-id your-open-id
# 显示历史康复激励记录清单(自动触发关键词:查看康复激励历史报告、康复激励日志清单等)
python -m scripts.smyx_rehab_motivation_encouragement_analysis --list --open-id your-open-id
# 输出精简报告
python -m scripts.smyx_rehab_motivation_encouragement_analysis --input rs.mp4 --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.smyx_rehab_motivation_encouragement_analysis --input rs.mp4 --open-id your-open-id --output result.json