← 返回 Skills 市场
kittenyang

CareMax Indicators

作者 Qitao Yang · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
114
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install caremax-indicators
功能描述
Query and track health indicators from CareMax Health API. Use when a user asks about health metrics, lab results, trends, or wants to quickly log everyday v...
使用说明 (SKILL.md)

CareMax Health Indicators

Requires caremax-auth as a sibling directory (../caremax-auth/, same layout as skills/caremax-auth + skills/caremax-indicators in this repo, or under ~/.agents/skills/). If missing: npx skills add KittenYang/caremax-skills and select caremax-auth.

What end users can do (plain language)

  • Browse and analyze their saved indicators: lists, categories, trends over time (labs and long-term metrics).
  • Quickly add a single reading for common day-to-day metrics — the same idea as the app’s 「快捷记一笔」: pick a familiar item (often things like 身高、体重、血压、心率、体温、腰围等,具体有哪些以当前账号下列出的可选项为准), enter a value and date, and it is stored like a normal indicator data point. No upload or report file required.

Agents should describe this in user-friendly terms (“帮你记一笔今天的体重”“看看现在能快捷记录哪些项目”) and only use the API steps below to implement it after the user is authenticated.

This skill also covers the agent/skill indicator endpoints under /api/skill/indicators/* for listing, categories, and trends.

Prerequisites — Auto-Auth (MANDATORY)

Working directory: this skill’s root folder (caremax-indicators/, sibling of caremax-auth/). Scripts in auth are reached with ../caremax-auth/scripts/.

# shorthand — run from caremax-indicators/
APICALL="bash ../caremax-auth/scripts/api-call.sh"
LIST_PRESETS="bash ../caremax-auth/scripts/list-system-presets.sh"
QUICK_LOG="bash ../caremax-auth/scripts/quick-log.sh"

If any script returns {"error":"no_credentials",...}immediately run bash ../caremax-auth/scripts/auth-flow.sh [base_url] in background. If the user specified a custom URL (e.g., http://localhost:8788), pass it as the argument. It opens the browser and auto-polls. Tell the user "please authorize in browser". Once it outputs authorized, retry.

List All Indicators

$APICALL GET /api/skill/indicators
# with category filter:
$APICALL GET "/api/skill/indicators?category=血常规"

Response fields: id (UUID, needed for trend), canonical_name, display_name, canonical_unit, category, latest_value, data_count

Get Indicator Categories

$APICALL GET /api/skill/indicators/categories

Get Indicator Trend

Important: Get the indicator UUID from the list endpoint first.

$APICALL GET "/api/skill/indicators/trend?id={indicator_uuid}"

Returns time-series: date, value, unit, reference_range, is_abnormal (0/1)

Quick log — same feature as 「快捷记一笔」 (authenticated user only)

Prefer the dedicated scripts (wrap api-call.sh with the same OAuth user token). Do not hand-roll curl.

Typical user intents: “记一下体重 70”“今天身高 175”“帮妈妈记血压 120/80” — always run list-system-presets.sh first so you use a valid preset_key and know default units; use --member when logging for a family profile.

1) List what the user can quick-log right now

$LIST_PRESETS

Response: presets[] — use preset_key for quick-log.sh; show display_name / canonical_unit when confirming with the user. Do not assume a fixed list of metrics in prose.

2) Save one value

$QUICK_LOG weight 72.5 --unit kg --date 2026-03-28
$QUICK_LOG height 175 --member \x3Cfamily_member_uuid>
  • Positional: preset_key, value (required).
  • Optional: --unit, --date YYYY-MM-DD (omit date → server default today), --member (family member UUID).

Lower-level equivalent (only if you need custom JSON)

$APICALL GET /api/indicators/system-presets
$APICALL POST /api/indicators/quick-log '{"preset_key":"weight","value":"72.5","unit":"kg","test_date":"2026-03-28","member_id":"..."}'

Recommended workflow (quick log)

# User: "帮我记身高" / "quick log my weight"
$LIST_PRESETS
# Match user wording to preset_key (or ask if ambiguous)
$QUICK_LOG \x3Cpreset_key> \x3Cvalue> [--date ...] [--member ...]
# Confirm aloud: value, unit, date, whose profile

Get Trends by Category

$APICALL GET "/api/skill/indicators/trends-by-category?category={category_name}"

Recommended Workflow

When user asks "show my creatinine trend":

# 1. List all indicators, find the matching one
$APICALL GET /api/skill/indicators
# 2. Extract the id (UUID) of the matching indicator from the response
# 3. Get trend data
$APICALL GET "/api/skill/indicators/trend?id={uuid}"
# 4. Present with dates, values, units, highlight abnormals

When user asks "what are my abnormal indicators":

# 1. Get all indicators
$APICALL GET /api/skill/indicators
# 2. Filter response for those with abnormal latest values
# 3. Present with values and reference ranges

Display Guidelines

  • Always show values with units (e.g., "98 μmol/L" not just "98")
  • Include reference ranges when available
  • Flag abnormal values clearly
  • For trends, show dates in chronological order
  • Chinese indicator names are standard — display them as-is
安全使用建议
This skill is coherent for accessing and logging CareMax health indicators, but it relies on a sibling component (caremax-auth) that performs authentication and contains the scripts the skill runs. Before installing/using: (1) verify the origin and contents of the ../caremax-auth scripts (or the npx package referenced) — review what network endpoints they contact and how they store tokens; (2) confirm you trust the code that will be executed locally, since the agent will run bash scripts; (3) be aware that using the skill will transmit sensitive personal health data to the CareMax API once authenticated; and (4) consider testing with a non-production account or inspecting the auth token storage location to ensure credentials are handled as you expect.
功能分析
Type: OpenClaw Skill Name: caremax-indicators Version: 1.0.0 The skill `caremax-indicators` manages health data by instructing the agent to execute bash scripts (`api-call.sh`, `quick-log.sh`) located in a sibling directory (`../caremax-auth/scripts/`). The `SKILL.md` file provides templates for constructing shell commands using user-provided values (e.g., `preset_key`, `value`, `date`), which introduces a high risk of shell injection vulnerabilities if the agent or the underlying scripts do not properly sanitize inputs. While the functionality aligns with the stated purpose of health tracking, the execution of shell scripts with user-derived arguments is a risky capability that lacks explicit safety constraints.
能力评估
Purpose & Capability
The skill says it will query and log CareMax health indicators and its runtime instructions only reference CareMax API endpoints and helper scripts (../caremax-auth/scripts/*). Requiring an auth helper alongside an indicators skill is coherent for this purpose.
Instruction Scope
The SKILL.md instructs the agent to execute local bash scripts (api-call.sh, list-system-presets.sh, quick-log.sh, auth-flow.sh) to perform API calls and to run an OAuth browser-based auth flow when needed. This is expected for an authenticated health-API integration but means the agent will execute local scripts that can run arbitrary commands and will transmit personal health data to the CareMax service. The instructions do not ask the agent to read unrelated system files or environment variables.
Install Mechanism
Instruction-only skill with no install spec and no code files in this package. No third-party downloads or archive extraction are requested, which is low-risk from an install perspective.
Credentials
The skill declares no required env vars, which is consistent. However it depends on a sibling caremax-auth component that will hold OAuth tokens/credentials and perform the auth flow; those tokens grant access to user health data. This is proportionate to the stated functionality, but you should review the sibling auth scripts to confirm how credentials are stored and used.
Persistence & Privilege
No always:true, no install, and no instructions to modify other skills or system-wide settings. The skill does request executing local scripts in a sibling directory but does not demand permanent agent-level privileges.
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 caremax-indicators
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /caremax-indicators 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
Initial publish to ClawHub
元数据
Slug caremax-indicators
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

CareMax Indicators 是什么?

Query and track health indicators from CareMax Health API. Use when a user asks about health metrics, lab results, trends, or wants to quickly log everyday v... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 114 次。

如何安装 CareMax Indicators?

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

CareMax Indicators 是免费的吗?

是的,CareMax Indicators 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

CareMax Indicators 支持哪些平台?

CareMax Indicators 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 CareMax Indicators?

由 Qitao Yang(@kittenyang)开发并维护,当前版本 v1.0.0。

💬 留言讨论