بنقرة واحدة
weight-loss-skill
يحتوي weight-loss-skill على 25 من skills المجمعة من NanoRhino، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.
Skills في هذا المستودع
Trigger on emotional signals, negative AND positive: body-image distress, guilt about eating, hopelessness, self-criticism — or pride, milestones, excitement about progress. Takes priority over ALL logging, data collection, and reminders — when a message carries both data (food/weight/exercise) and emotion, emotional presence comes FIRST; log later or briefly after.
Reference companion for expert interventions. Trigger when the prompt carries a 'Pending Expert Intervention (auto-injected)' section — the injected file is the runtime authority; read this skill when you need the full workflow background (intervention kinds, negotiation state machine, logging, file lifecycle).
Creates calorie-controlled diet templates and weekly meal plans from the user's calorie target and preferences (multiple diet modes). Trigger on: meal/diet plan requests, 'what should I eat to lose weight', '帮我做个饮食计划', meal prep and portion-control help, recipe suggestions tied to weight loss. Requires a calorie target (from PLAN.md or user-stated). On-the-spot restaurant/dining decisions → restaurant-meal-finder.
Per-trigger execution logic for daily reminders. Runs pre-send checks, composes meal/weight reminder messages, and manages recall messages. Use this skill when: a cron job fires and needs to decide whether/what to send. Do NOT use for cron management, lifecycle transitions, or reminder settings — that is notification-manager's job.
Cron infrastructure and reminder lifecycle (Active → Recall → Weekly/Monthly → Silent). Use when: onboarding completes (bootstrap meal/weight reminder crons), reminder timing/settings change, or another skill needs cron state verified/fixed. Leave/vacation requests → leave-manager. Composing reminder content → notification-composer. User-requested reminder CRUD → reminder-manager.
Returns meal-logging streak data (current_streak, pending_milestone) — called BY other skills (notification-composer at Stage-1 meal reminders; weekly-report), never a standalone conversation skill. Only user-triggered case: explicit streak questions ('我连续打卡几天了', 'what's my streak'). Never proactively mention streaks; silence after a break.
新用户首次接入或主动更新画像时使用。⚠️ 必须先 read 正文再回——首条消息规则(不自我介绍/不问名字/加好友自动消息 NO_REPLY/每轮 ≤2 题)在正文里,凭直觉发挥会违规。所有教练技能依赖它的输出。拿不准就触发。
Personal nutritionist skill for weight loss goal-setting. Creates a single personalized plan with BMI analysis, TDEE-based calorie targets, and an estimated completion date. Use this skill when the user mentions weight loss goals, diet planning, calorie targets, BMI, TDEE, or asks for a weight loss plan. Also trigger when user wants to calculate how long to reach a target weight.
Renders Markdown plans (PLAN.md / MEAL-PLAN.md / EXERCISE-PLAN.md) to styled HTML pages with presigned URLs, or PDF. Trigger when a planner skill finishes generating a plan, or the user asks for their plan link ('我的计划链接') / the old link expired. Channel whitelist applies — non-listed channels (wechat) get inline text from the calling skill.
Internal memory maintenance — NOT triggered by user messages. Invoked by the agent after conversations and by scheduled consolidation runs (short/medium/long-term promotion and cleanup).
Send the 减脂档案 mini-program card when the user asks for overall progress/data/trajectory: '减脂档案', '我的数据', '减脂曲线', '体重曲线', 'my progress'. NOT for '今天/今日' single-day queries → personal-data-query; NOT '周报/这周' → weekly-report.
Designs personalized training programs. Trigger on workout-plan requests: 'make me a workout', 'gym routine', 'how should I train', 'I want to start working out', '帮我制定训练计划', '运动方案'. NOT for logging completed workouts → exercise-tracking.
Logs workouts, estimates calories burned, weekly exercise summaries. Trigger on ANY physical-activity mention — 'I ran...', 'went to the gym', '跳操半小时', even casual ('took the stairs') — and fitness-device data (Apple Watch/Garmin/Strava). When in doubt, trigger. NOT for plan requests → exercise-planning.
Designs and manages healthy habits (Atomic Habits methodology). Trigger on: foodless behavior self-reports ('我喝水很少', 'I skip breakfast', '我吃饭太快'), habit requests ('我想养成早睡的习惯'), tracking/querying active habits, and right after onboarding completes (recommend the first habit). No own reminders — check-ins woven into meal conversations.
Trigger when the user wants to pause proactive reminders for a period. MUST persist to data/leave.json (the system source of truth — cron auto-silences during leave, auto-resumes after); an empathetic reply without calling this skill = the leave never takes effect and cron keeps disturbing the user. Trigger on ANY pause signal regardless of wording. Explicit: '暂停提醒', '请假', 'pause reminders'. Implicit (MUST also trigger): '过段时间再说', '别烦我', '最近不想减肥', '出差一周', '节假日/春节期间不方便', '这几天聚餐多', '出去玩几天'. Also for ending leave early: '我回来了', '继续吧', 'I'm back'. NOT for one-off '今天不用提醒了' (single skip ≠ leave).
Follow-up onboarding for users migrated from the WeChat miniprogram: fills the coaching setup the miniprogram skipped (meal schedule, reminders, check-in intro). Trigger ONLY when workspace has `.from-miniprogram.json` AND lacks `.migration-followup-completed`. One-shot — never on subsequent messages.
User-requested reminder CRUD — covers both user-created custom reminders AND system meal/weight reminders. Trigger on: create ('提醒我...', '两分钟后提醒我', 'remind me...'), view ('我有哪些提醒'), change ('把午餐提醒改到12点'), delete ('取消喝水提醒', 'cancel my reminder'). Pausing ALL reminders for a period (请假) → leave-manager. System reminder bootstrap at onboarding → notification-manager.
Real-time dining recommendations from real nearby restaurants: what to order when eating out, delivery/takeout/convenience-store picks that fit the user's calories. Trigger: '附近吃什么', '中午外面吃什么好', '想点外卖有什么推荐', 'I'm at a restaurant, what should I order'. Weekly-plan restaurant options → meal-planner.
generate personalized weekly progress reports for Nano Rhino users. Use for manual weekly report requests such as "weekly report", "周报", "这周怎么样", and for scheduled Sunday 21:00 user-local cron runs. Always generate a clickable report URL using the bundled weekly report scripts; never return a text-only report.
Weight CRUD, unit conversion, everyday trend judgment (encourage/noise/plateau). ANY message containing a weight number — '我XX斤', '掉了X斤', '称了XX', 'I weigh...' — MUST trigger and be saved to data/weight.json BEFORE replying; never acknowledge without saving. Also: trend queries ('体重趋势'), corrections, unit changes ('改成斤'). Sustained upward trend needing cause analysis → weight-gain-strategy.
Tracks food intake: calories, macros, daily targets, cumulative feedback. Trigger on ANY food mention — photos, meal descriptions, past-tense ('I ate...'), about-to-eat, even casual ('grabbing a coffee') — and calorie-target changes. NOT for foodless behavior patterns ('I skip breakfast', '我喝水很少') → habit-builder.
One-time cron-only skill (never user-triggered): checks if the user's actual eating pattern fits a different diet mode, then self-destructs.
Query today's diet data: intake, remaining calories, daily progress. Trigger: '今天吃了多少', '今日进度', '今天还剩多少', 'how many calories today'. NOT for logging food → diet-tracking-analysis; NOT weight recording → weight-tracking; NOT overall trajectory/档案 → diet-profile-card; NOT '周报' → weekly-report.
Deep intervention for sustained upward weight trends. Trigger: consecutive increases flagged by post-weigh-in checks, or explicit questions ('体重怎么涨了', 'why am I gaining weight'). Graduated support: reassurance → cause analysis → temporary adjustments. Recording weigh-ins and routine trend judgment → weight-tracking. NOT when emotional distress needs priority → emotional-support; NOT when weight-focus should be avoided (history_of_ed / avoid_weight_focus flags).
Upload local files to JD Cloud OSS and get presigned URLs (15 min expiry). Use when needing to share local files via URL, send images to chat channels that require public URLs, or upload any file to cloud storage. Supports images, PDFs, videos, and any file type.