← 返回 Skills 市场
klcintw

Health Auto Log

作者 klcintw · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
356
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install health-auto-log
功能描述
Automatically detect and log health data (weight, blood sugar, exercise) to AX3 system. Use when user sends health measurements via WhatsApp or other messagi...
使用说明 (SKILL.md)

Health Auto Log

Overview

Automatically detect health metrics from user messages and record them to AX3 Personal system. Supports weight, blood sugar, and exercise time tracking with flexible input formats.

When to Use This Skill

Trigger this skill when user messages contain:

  • Weight measurements (e.g., "體重69.8公斤", "69.8kg", "69.8")
  • Blood sugar readings (e.g., "血糖120", "120 mg/dL")
  • Exercise time (e.g., "跑步機30分", "跑步30")

Quick Start

Use the record_health_data.py script to process any message:

python3 scripts/record_health_data.py "體重69.8公斤"

The script will:

  1. Extract health metrics from the message
  2. Validate the values are within reasonable ranges
  3. Record to AX3 using mcporter
  4. Return confirmation with record IDs

Supported Metrics

1. Weight (體重)

Habit ID: 1
Unit: kg
Range: 40-200 kg

Supported formats:

  • 體重69.8公斤
  • 69.8kg
  • 69.8 (plain number)

2. Blood Sugar (血糖)

Habit ID: 4
Unit: mg/dL
Range: 50-500 mg/dL

Supported formats:

  • 血糖120
  • 120 mg/dL

3. Running Time (跑步機)

Habit ID: 2
Unit: minutes

Supported formats:

  • 跑步機30分
  • 跑步30

Workflow

Automatic Detection Flow

  1. Receive message from WhatsApp or other channel
  2. Run script with message text: python3 scripts/record_health_data.py "\x3Cmessage>"
  3. Extract metrics using regex patterns
  4. Validate values are in reasonable ranges
  5. Record to AX3 via mcporter call to ax3-personal.record_habit
  6. Confirm with user showing what was recorded

Example Usage

# Single metric
python3 scripts/record_health_data.py "體重69.8公斤"
# Output: ✅ 體重 69.8 kg 已記錄

# Multiple metrics in one message
python3 scripts/record_health_data.py "體重69.8公斤 血糖120"
# Output: 
# ✅ 體重 69.8 kg 已記錄
# ✅ 血糖 120 mg/dL 已記錄

Integration Pattern

When a user sends a health-related message:

  1. Call the script with the message text
  2. Parse the JSON output to check if data was detected
  3. If detected, respond with confirmation (e.g., "收到！69.8 kg 已記錄 📝")
  4. If not detected, reply normally without mentioning the skill

Error Handling

The script includes validation:

  • Out of range values are ignored (e.g., weight of 500kg won't be recorded)
  • Invalid formats are silently skipped
  • mcporter failures are captured and returned in the JSON output

Resources

scripts/record_health_data.py

Python script that handles:

  • Pattern matching for various health data formats
  • Value validation and range checking
  • AX3 API calls via mcporter
  • JSON output for programmatic integration

The script can be called directly or integrated into message handling workflows.

安全使用建议
This skill's behavior is plausible (auto-detect health metrics and call AX3), but the implementation is sloppy and potentially privacy-sensitive: it hard-codes a specific user's mcporter config path and invokes an external 'mcporter' binary that was not declared. Before installing or using it, ask the author to: (1) explain and remove the hard-coded path (make the config path or mcporter options configurable via env var or parameter), (2) declare 'mcporter' as a required binary and document what its config contains, (3) confirm whether mcporter.json contains secrets and whether those will be used/exposed, and (4) run the script in a safe sandbox to verify it doesn't read unexpected files. Do not install or give this skill access to production health data until these issues are resolved.
功能分析
Type: OpenClaw Skill Name: health-auto-log Version: 1.0.0 The skill bundle is benign. The `SKILL.md` accurately describes the skill's purpose and how the agent should invoke the `record_health_data.py` script with user input. The Python script `scripts/record_health_data.py` securely handles user input by using regular expressions to extract only numeric values, performing type conversions (float/int), and validating these values within reasonable ranges. Crucially, it uses `subprocess.run` with a list of arguments, preventing shell injection, and the numeric values passed to the `mcporter` command are sanitized. There is no evidence of data exfiltration, persistence mechanisms, or malicious prompt injection attempts against the agent.
能力评估
⚠ Purpose & Capability
The SKILL.md describes recording to AX3 via 'mcporter', but the skill metadata lists no required binaries or config paths. The script actually invokes the external 'mcporter' binary and hard-codes a user-specific config file (/Users/klcintw/clawd/config/mcporter.json). Those dependencies are not declared and are not proportionate to the manifest.
⚠ Instruction Scope
Runtime instructions tell the agent to run the included script, which is fine, but the script will call an external tool and attempt to use a specific local config file. The SKILL.md mentions mcporter but does not disclose the hard-coded config path or the expectation that a local mcporter installation and user config exist. That hidden file access is out-of-band for what a user would expect.
ℹ Install Mechanism
There is no install spec (instruction-only + code file) so nothing is written during install. However the script relies on an external binary ('mcporter') being present on PATH; the skill metadata did not declare this required binary. No network/download install risk is present.
⚠ Credentials
The skill declares no required env vars or config paths, yet the script references a concrete config file path likely to contain credentials for mcporter/AX3. This is disproportionate: the code can read or rely on local credentials without declaring or requesting them explicitly.
✓ Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent platform privileges. It does not modify other skills or agent-wide settings.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install health-auto-log
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /health-auto-log 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Auto-record health data to AX3
元数据
Slug health-auto-log
版本 1.0.0
许可证 —
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Health Auto Log 是什么？

Automatically detect and log health data (weight, blood sugar, exercise) to AX3 system. Use when user sends health measurements via WhatsApp or other messagi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 356 次。

如何安装 Health Auto Log？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install health-auto-log」即可一键安装，无需额外配置。

Health Auto Log 是免费的吗？

是的，Health Auto Log 完全免费（开源免费），可自由下载、安装和使用。

Health Auto Log 支持哪些平台？

Health Auto Log 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Health Auto Log？

由 klcintw（@klcintw）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 留言讨论