skills.rest
MagicDBH
MagicDBHCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Sensor-in-the-Loop Personalized Health Assistant for OpenClaw

Summarize wearable CSV sensor data and compute 7-day health trends.

Updated Mar 29, 2026
Search Tags:#personalization#query rewriting#wearable analytics#sleep coaching#stress recovery#time-series trends
One-click install
npx skills add https://github.com/MagicDBH/HealthyAssistant --skill sensor-in-the-loop-personalized-health-assistant-for-openclaw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Sensor-in-the-Loop Personalized Health Assistant for OpenClaw
Source: https://github.com/MagicDBH/HealthyAssistant/tree/main
Command: npx skills add https://github.com/MagicDBH/HealthyAssistant --skill sensor-in-the-loop-personalized-health-assistant-for-openclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Sensor-in-the-loop health coaching turns raw wearable metrics into a state-aware, personalized plan for sleep, recovery, exercise, travel readiness, and work/meeting performance.

Core Features & Use Cases

  • Daily health snapshot + 7-day trends: Loads a user’s real CSV data to summarize activity, sleep, and stress/recovery signals with rolling-window context.
  • Question classification and context rewriting: Categorizes the user’s query into health decision types and rewrites it into a state-grounded prompt for downstream response generation.
  • Structured OpenClaw payload output: Produces a JSON context with answer focus guidance so the LLM can respond in Chinese with prioritized, actionable recommendations.

Use case example: A user asks before a big meeting, “我明天要开会，今天该怎么调整？”. The skill builds daily and 7-day summaries from jian.csv, classifies the question as work/meeting, rewrites the query with sleep/stress/recovery context, and outputs a payload for an LLM-driven actionable plan.

Quick Start

Ask in Chinese for a state-aware recommendation, for example: 我明天要开会，今天该怎么调整？

Frequently Asked Questions about Sensor-in-the-Loop Personalized Health Assistant for OpenClaw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn wearable sensor data into personalized health recommendations?▼

You can generate personalized health recommendations by loading wearable sensor data from a CSV file to compute 7-day trends and daily snapshots for stress recovery and sleep coaching.

Can I use my own CSV file for wearable analytics and sleep coaching?▼

Yes, you can import your own CSV file containing wearable metrics to compute rolling 7-day aggregations and generate localized query rewriting for sleep coaching scenarios.

What's the best way to prepare for a meeting using wearable time-series trends?▼

The best way to prepare for a meeting using time-series trends is to classify your query into a work or meeting scenario and apply rolling-window context to your stress and recovery signals.

How does query rewriting work for stress recovery and exercise scenarios?▼

Query rewriting for stress recovery and exercise scenarios works by categorizing your health question type and generating a state-grounded JSON payload with answer focus guidance for the LLM.

Does this health assistant tolerate missing values in wearable sensor data?▼

Yes, the health assistant applies safe numeric handling with missing-value tolerance when processing your wearable sensor data to ensure accurate 7-day metric aggregation.

What dependencies do I need to run personalized sleep coaching analysis?▼

You need pandas and numpy installed to run personalized sleep coaching analysis that performs daily snapshot extraction and rolling 7-day metric aggregation from your CSV data.

Related Skills

Explore More Data & Analytics Skills→
GeneralReasoningGeneralReasoning
4

csv-processing

Read, clean, transform, and export CSV sensor data with pandas.

Official
Intermediate
oaustegardoaustegard
137

asking-questions

Identify ambiguous user requests and ask targeted clarifying questions.

Community
Basic
Axel-DaMageAxel-DaMage
2

pandas-pro

Automate pandas DataFrame operations for cleaning, aggregation, and time series analysis.

Community
Advanced
cobuildwithuscobuildwithus
11

sleep-improvement

Analyze wearable sleep data and environmental factors to generate personalized sleep improvement recommendations.

Official
Intermediate