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 mediwise-health-trackergit 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/mediwise-health-tracker)<a href="https://agentmods.dev/skills/juneyaooo/mediwise-health-suite/mediwise-health-tracker"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/mediwise-health-tracker/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/mediwise-health-tracker"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/mediwise-health-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.06398 |
| Opus 5 | $0.00018 | $0.03199 |
| Sonnet 5 | $0.00007 | $0.01280 |
| Haiku 4.5 | $0.00004 | $0.00640 |
Grade A, and why
mediwise-health-tracker 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 today.
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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MediWise · 健康档案 Skill
健康档案与病程记录 Skill。所有操作通过 {baseDir}/scripts/ 下的 Python 脚本完成，默认输出 JSON，再转成自然语言回复给用户。
当用户问”你可以做什么”时，记得主动提到：除了健康档案、指标记录、提醒、健康卡片外，还可以根据最近的描述和历史记录先整理一段”就医前摘要”，并在需要时继续生成图片或 PDF，方便给医生快速了解病情。
适用场景
- 添加或管理家庭成员信息
- 记录就诊经历（门诊/住院/急诊）、症状/诊断/用药/检验/影像检查结果
- 记录日常健康指标（血压/血糖/心率/体温等）
- 查询病程历史或用药记录、生成健康时间线或摘要、查看全家健康概况
- 发送体检报告图片或化验单需要识别录入
- 设置用药提醒、健康指标测量提醒、复查提醒，或获取状态汇总、健康卡片、就医前资料摘要图
- 规划就诊流程（预约 → 就诊前汇总 → 记录诊断结果 → 复诊追踪）
- 随口提到健康问题（如”最近膝盖有点疼”）需要记录并定期跟进
核心工作流
0. 确认个人本地模式
当前公开版本只面向一个本地用户管理自己和多位家人的档案。安装 Agent 已负责配置个人模式；不要再让普通用户配置共享身份、群聊路由或 owner_id。
1. 按姓名与身份解析成员
写入或查询前调用 resolve-member：
- 没有任何成员：询问用户姓名，确认后调用
add-member创建“姓名（本人）”。 - 只有一个且身份为“本人”：用户没说姓名时可以默认选择本人。
- 已有两位及以上成员：写入时必须有姓名；用户没说姓名就先询问，不能猜。
- 用户说了“爸爸”“妈妈”等关系：只有该关系唯一时才可解析，并在写入前复述最终的“姓名（身份）”。
- 同名或同身份出现多个匹配：同时询问姓名和身份进行消歧。
成员列表和确认回复始终显示“姓名（身份）”，例如“张建国（父亲）”“王丽（母亲）”。不得只展示内部 ID。
2. 选择录入路径
- 简短指标文本：优先
quick_entry.py - 复杂文本、就诊、用药、检验：用
smart_intake.py或对应业务脚本 - 图片 / PDF / 多附件：走视觉录入流程
- 录入后发现异常指标、新诊断或用药变化：用
log-health-note动作记录并跟进
3. 查询后做自然语言整理
python3 {baseDir}/scripts/query.py summary --member-id <id>
python3 {baseDir}/scripts/query.py timeline --member-id <id>
python3 {baseDir}/scripts/query.py active-medications --member-id <id>
python3 {baseDir}/scripts/query.py family-overview
不要把 JSON 原样贴给用户；改写成趋势、摘要、时间线和清晰列表。
快速命令
常用录入
结构化数据可直接调用对应动作写入：
| 动作 | 说明 | 关键参数 |
|---|---|---|
add-member |
创建家庭成员档案 | name、relation；可选 gender、birth_date、blood_type、allergies、medical_history、phone、emergency_contact、emergency_phone、timezone |
get-member / update-member / delete-member |
查看、更新或删除成员档案 | member_id；更新时只传需要修改的字段 |
resolve-member |
按姓名/身份解析目标成员 | 可选 name、relation；多成员时用于消歧 |
add-visit |
添加就诊记录 | member_id, visit_type, visit_date；可选 hospital/department/diagnosis |
add-symptom |
添加症状记录 | member_id, symptom；可选 severity/visit_id/onset_date |
add-medication |
添加用药记录 | member_id, name；可选 dosage/frequency/visit_id/purpose |
add-metric |
添加健康指标 | member_id, type, value；可选 measured_at/source/context |
get-metrics / delete-metric |
按类型与日期范围查询或删除指标 | 查询可选 type/start_date/end_date/limit；删除传记录 id |
add-lab-result / add-imaging |
直接写入已确认的检验或影像结构化结果 | member_id、名称、日期与已确认内容 |
snapshot-save / snapshot-get / snapshot-history / snapshot-trend |
保存或查询每日健康快照 | member_id；查询单日时传 date，历史和趋势可传 days |
What ships with it
46 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 277 B
- DREAM.md 7.6 KB
- index.js 31 KB runs code
- package.json 301 B
- references/cycle-attachments-local-scope.md 3.1 KB
- references/drug-safety-health-card.md 5.6 KB
- references/intake-query-vision.md 5.7 KB
- references/test-vision.jpg 127 KB
- references/visit-prep.md 3.7 KB
- scripts/api_client.py 7.0 KB runs code
- scripts/attachment.py 24 KB runs code
- scripts/briefing_report.py 80 KB runs code
- scripts/checkup_report.py 20 KB runs code
- scripts/chronic_disease.py 15 KB runs code
- scripts/config.py 15 KB runs code
- scripts/cycle_tracker.py 15 KB runs code
- scripts/daily_snapshot.py 14 KB runs code
- scripts/doctor_visit_report.py 35 KB runs code
- scripts/dream.py 15 KB runs code
- scripts/drug_interaction.py 25 KB runs code
- scripts/embedding_provider.py 5.7 KB runs code
- scripts/export.py 16 KB runs code
- scripts/health_advisor.py 25 KB runs code
- scripts/health_db.py 50 KB runs code
- scripts/health_memory.py 9.6 KB runs code
- scripts/health_metric.py 8.9 KB runs code
- scripts/html_screenshot.py 7.5 KB runs code
- scripts/medical_record.py 30 KB runs code
- scripts/medication_log.py 5.2 KB runs code
- scripts/member.py 15 KB runs code
- scripts/memory.py 26 KB runs code
- scripts/metric_utils.py 4.3 KB runs code
- scripts/openfda_query.py 6.9 KB runs code
- scripts/privacy.py 7.7 KB runs code
- scripts/query.py 22 KB runs code
- scripts/quick_entry.py 8.0 KB runs code
- scripts/reminder.py 22 KB runs code
- scripts/setup.py 63 KB runs code
- scripts/smart_intake.py 48 KB runs code
- scripts/test_authorization.py 13 KB runs code
- scripts/test_briefing_report.py 5.2 KB runs code
- scripts/test_health_scope.py 4.0 KB runs code
- scripts/test_smart_intake.py 40 KB runs code
- scripts/validators.py 6.9 KB runs code
- scripts/vector_search.py 20 KB runs code
- scripts/visit_lifecycle.py 19 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.
- today Changed 597c2b0330e6
- 12d ago First seen · 367 lines · 37 tokens per session scan A 18d324f7a615
mediwise-health-tracker is a skill published in the GitHub repository JuneYaooo/mediwise-health-suite (29 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 6,398 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
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.