Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add JuneYaooo/mediwise-health-suite --skill wearable-syncgit clone --depth 1 https://github.com/JuneYaooo/mediwise-health-suiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/juneyaooo/mediwise-health-suite/wearable-sync)<a href="https://agentmods.dev/skills/juneyaooo/mediwise-health-suite/wearable-sync"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/wearable-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/juneyaooo/mediwise-health-suite/wearable-sync"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/wearable-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01963 |
| Opus 5 | $0.00018 | $0.00981 |
| Sonnet 5 | $0.00007 | $0.00393 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
wearable-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MediWise · 可穿戴数据导入 Skill
把用户明确提供的可穿戴导出文件读取、标准化并写入 MediWise 健康指标。当前公开流程只面向个人本地 Agent 环境。
可用性分级
| Provider | 状态 | 数据来源 | 说明 |
|---|---|---|---|
| Apple Health | ✅ 已验证 | export.zip / export.xml |
支持文件检查、导入、标准化与去重 |
| Gadgetbridge | ✅ 已验证 | SQLite 导出数据库 | 只读导入常见活动数据表 |
| Garmin Connect | 🧪 实验性 | 非官方 Garmin Connect 接口 | 没有安全的免代码凭据输入能力时不得引导绑定 |
| Huawei Health Kit | ⛔ 暂不可用 | OAuth API | 授权回调尚未完成 |
| Zepp / 小米云账号 | ⛔ 暂不可用 | 非官方账号接口 | 账号兼容性和凭据处理未达到稳定发布标准 |
| OpenWearables | ⛔ 暂不可用 | 统一 API | 当前是 Stub |
不得因为代码中存在 Provider 类，就把实验性或未完成来源描述成“已支持”。
用户交互规则
- 用户只需要用自然语言提出导入请求并上传导出文件。
- 不要求普通用户运行 Python、Node.js、Shell、pip 或其他命令。
- 不在聊天中索要 API Key、账号密码、token 或其他凭据。
- 一个本地用户可以管理多位家人：只有唯一“本人”档案时可默认本人；出现多位成员后必须按姓名确认目标，不得根据文件内容猜测。
- 不把当前 MediWise 数据目录用于群聊机器人或多人共享服务。
- 不修改用户提供的 Apple Health 或 Gadgetbridge 原始文件。
- 完成后必须报告新增数量、重复跳过数量、实际指标类型和时间范围；不能只回复“同步成功”。
如果 action 返回个人模式未配置、依赖缺失或安装路径错误，应让具备本机访问权限的 AI 助手修复安装，不要把代码命令转交给普通用户。
Apple Health 导入流程
用户侧准备
指导用户在 iPhone 中：
- 打开“健康”App。
- 点击右上角头像。
- 选择“导出所有健康数据”。
- 保存或上传系统生成的
export.zip。
导出包包含敏感健康数据，只能交给用户信任的个人本地 Agent。
Agent 执行顺序
- 调用
resolve-member：唯一“本人”可默认；有多位成员时按姓名确认，并复述“姓名（身份）”。 - 确认附件已落到当前 Agent 可读取的本地路径，扩展名为
.zip或.xml。 - 调用
device-add，Provider 使用apple_health。 - 调用
device-auth，把附件本地路径作为export_path。 - 调用
device-test检查标准export.xml、XML 完整性和 Apple Health 根节点。 - 调用
sync-device导入。 - 使用
sync-device返回的provider、member、metric_types、metric_stats和time_range汇总本次结果；需要查看具体记录时再查询健康指标。
Apple Health 导出是手动快照，不是实时流。用户再次上传新导出包时可重新导入；系统会按成员、指标类型、测量时间和来源跳过重复记录。
Apple Health 可识别指标
- 心率、步数、血氧、睡眠
- 体重、身高、体脂
- 血糖、血压
- 活动卡路里
实际导入项以文件内容为准。不得看到 Apple Watch 型号后就声称上述指标全部存在。
Gadgetbridge 导入流程
用户侧准备
此流程只适合已经使用 Gadgetbridge 管理设备的用户。指导用户在 Gadgetbridge App 的“设置”或“数据库管理”中导出数据库，然后上传 Gadgetbridge 或 Gadgetbridge.db 文件。
设备兼容性以 Gadgetbridge 官方支持列表为准。不要声称所有小米、Amazfit 或华为设备都适用。
Agent 执行顺序
- 调用
resolve-member：唯一“本人”可默认；有多位成员时按姓名确认，并复述“姓名（身份）”。 - 确认附件已落到当前 Agent 可读取的本地路径。
- 调用
device-add，Provider 使用gadgetbridge。 - 调用
device-auth，把附件本地路径作为export_path。 - 调用
device-test，确认它是可读取的 SQLite 数据库且包含已知活动数据表。 - 调用
sync-device导入。 - 查询该成员本次导入后的健康指标，汇总类型、条数和时间范围。
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 240 B
- index.js 4.2 KB runs code
- package.json 334 B
- scripts/device.py 17 KB runs code
- scripts/normalize.py 14 KB runs code
- scripts/providers/__init__.py 222 B runs code
- scripts/providers/apple_health.py 13 KB runs code
- scripts/providers/base.py 2.3 KB runs code
- scripts/providers/gadgetbridge.py 7.2 KB runs code
- scripts/providers/garmin.py 28 KB runs code
- scripts/providers/huawei.py 9.7 KB runs code
- scripts/providers/openwearables.py 1.1 KB runs code
- scripts/providers/zepp.py 13 KB runs code
- scripts/sync.py 17 KB runs code
- test_data/generate_sample.py 4.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 155 lines · 36 tokens per session scan A f2485059eb91
wearable-sync is a skill published in the GitHub repository JuneYaooo/mediwise-health-suite (28 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,963 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
ai-claim-checker
Evaluate factual claims in AI-generated text and teach a lightweight verification habit. Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy.
cv-classification
Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.
nlp-alignment
Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.