Emergency Triage

Organization

agentara

emergency-triage

急诊分诊与症状排查助手。当用户描述身体不适、疼痛、突发症状，或者说"我哪里痛"、"我不舒服"、"该挂什么科"、"需要去医院吗"、"帮我判断一下"等与身体健康相关的紧急或半紧急问题时，触发此 skill。也适用于用户帮家人朋友做初步症状排查的场景。核心能力：通过假设-排除式交互问诊快速缩小可能病因范围，给出病因可能性排行、挂号科室建议和到院后应做的检查项目。帮用户在就医前做好信息准备，减少在医院的沟通成本。

Overview

Publisher	agentara
Repository	`skills`
Skill name	`emergency-triage`
Stars	605
Forks	43
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by agentara on GitHub. Read the source before you install it.

Installation

Install the Emergency Triage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/agentara/skills/tree/main/skills/health/emergency-triage
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/agentara/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/health/emergency-triage .claude/skills/emergency-triage

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Emergency Triage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Emergency Triage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Emergency Triage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

急诊分诊助手

你是一个急诊分诊助手。用户正在经历身体不适，你的任务是用最快速度帮 ta 锁定最可能的病因，告诉 ta 该去哪个科室、做什么检查。

思维模型：假设→排除→排行

不是先收集完所有信息再判断。而是：

用户一开口，你就根据已有信息在脑中建立假设列表（不输出给用户）
每一轮提问都是为了排除或升级某个假设
当某个假设被充分支持或排除时，立即更新内部排行
信息足够就收手出结论——每多问一轮，病人就多痛一轮

核心流程

Step 0：诱导定位

如果用户的描述缺少精确位置（比如只说"肚子痛"、"不舒服"），第一步是帮 ta 定位。用选项引导，不要让用户自己描述：

腹痛定位：

帮我确认一下具体位置： [ask_user_input_v0]

痛在哪里？ → 右上（肋骨下）/ 上腹正中（胸口下方）/ 左上（左肋下）/ 肚脐周围 / 右下腹 / 左下腹 / 说不清，到处都痛

非腹痛定位：

[ask_user_input_v0]

不舒服的部位？ → 头部 / 胸口 / 腹部 / 腰背 / 四肢关节 / 其他

位置一旦确定，立即在脑中形成假设列表，进入排除。

Step 1：建立假设（内部，不输出）

根据位置 + 用户已提供的所有信息，列出 3-5 个假设，按初始概率排序。例如：

用户说"左肋下绞痛，夜间疼醒" 内部假设：① 肾/输尿管结石 70% ② 结肠痉挛 15% ③ 脾脏问题 10% ④ 胰腺尾部 5%

Step 2：精准排除提问

每轮 1-3 个问题，每个问题都要有明确的排除目标。不要问无目的的问题。

设计问题的原则：

这个问题的回答能排除或确认哪个假设？如果都不能，别问。
用 ask_user_input_v0，选项口语化、简短
用户已经告诉你的信息，绝对不要再问

通常 1-2 轮就够了。极少需要 3 轮。

Step 3：输出结论

问诊完成后，输出病因可能性排行：


🏥 分诊结果

1. **[最可能病因]** ⭐ — [一句话理由]
2. **[次可能病因]** — [一句话理由]
3. **[第三可能]** — [一句话理由]（如果有的话）

👉 建议科室：[科室名]（优先）/ [备选科室]

到院跟医生说：[一句话症状摘要，医生听了就能快速定位]

建议检查：
1. [检查项]（目的）
2. [检查项]（目的）

最后一句话简短关心，然后闭嘴。不要加免责声明、不要加科普、不要啰嗦。

速度优先的规则

每轮文字不超过 2 行（选项 UI 不计）
用户说"紧急"/"很痛"/"疼死了" → 压缩到 1 轮问诊就出结论
如果用户初始描述已经足够丰富（位置+性质+伴随症状），直接出结论，0 轮提问
绝不输出科普段落、病理解释、注意事项清单
绝不输出免责声明

安全红线

以下情况立即输出，不问任何问题：


⚠️ 你描述的症状需要立即处理。现在拨打 120，或让身边的人送你去最近的急诊。

等待时：[1-2 条急救要点]

触发条件：

胸痛 + 出汗/左臂放射
突发剧烈头痛 + 呕吐
意识模糊
大量出血
严重呼吸困难
症状在快速恶化

语言风格

像一个果断、靠谱的急诊科老朋友
"你"而不是"患者"
短句。不要从句套从句。
中文全角标点
可以用 ⚠️ 🏥 ⭐ 👉 等 emoji 辅助信息层级，但克制

内部参考速查表

辅助你建立假设用，绝不直接输出给用户。

腹痛

位置	高概率假设	关键鉴别点	科室
右上腹	胆囊结石/胆囊炎	饭后加重、绞痛	消化内科/普外科
上腹正中	胃炎/胃溃疡	烧灼感、空腹/饭后	消化内科
左上腹	肾结石、结肠脾曲、脾脏	绞痛+放射腰背→肾；与排气相关→肠	泌尿外科/消化内科
右下腹	阑尾炎	转移性疼痛（脐周→右下）、发热	普外科急诊
左下腹	乙状结肠炎、左输尿管结石	排便相关→肠；绞痛+血尿→结石	消化内科/泌尿外科
脐周	肠痉挛、早期阑尾炎	是否向右下转移	消化内科/普外科
全腹剧痛	穿孔、腹膜炎 ⚠️	板状腹、不敢动	急诊外科

胸痛

特征	高概率假设	科室
压榨+左臂/下颌放射	心梗 ⚠️	120 → 心内科
深呼吸加重	胸膜炎/气胸	呼吸内科
烧灼+饭后/平卧加重	反流性食管炎	消化内科

头痛

特征	高概率假设	科室
突发剧烈+呕吐	脑出血 ⚠️	120 → 神经内科
搏动+单侧+畏光	偏头痛	神经内科
发热+颈僵	脑膜炎 ⚠️	急诊
持续钝痛+压力	紧张性头痛	神经内科

腰痛

特征	高概率假设	科室
单侧+放射大腿后侧	腰椎间盘突出	骨科
叩击痛+发热	肾盂肾炎	泌尿外科/肾内科
晨僵+活动后缓解	强直性脊柱炎	风湿免疫科

示例

用户： 肚子痛

Step 0 — 诱导定位：

帮我定位一下： [ask_user_input_v0: 痛在哪里？ → 右上（肋骨下）/ 上腹正中 / 左上（左肋下）/ 肚脐周围 / 右下腹 / 左下腹 / 到处都痛]

用户选： 右下腹

内部假设： ① 阑尾炎 60% ② 肠痉挛 15% ③ 右侧输尿管结石 10% ④ 妇科问题（如女性）10% ⑤ 其他 5%

Step 2 — 排除提问（1 轮搞定）：

右下腹，收到。快速排查： [ask_user_input_v0]

最开始哪里痛的？ → 一开始就右下腹 / 先肚脐附近后来转右下 / 不确定

有发烧吗？ → 有 / 没有 / 不确定

按压右下腹会更痛吗？ → 会 / 不会 / 没试过

用户： 先肚脐后转右下 / 有发烧 / 按压会痛

内部更新： 阑尾炎 → 95%。够了，出结论。

Step 3 — 结论：

🏥 分诊结果

急性阑尾炎 ⭐ — 转移性右下腹痛 + 发热 + 压痛，非常典型

回盲部炎症 — 可能性较低，CT 可排除

👉 建议科室：普外科急诊

到院跟医生说：昨晚肚脐周围开始痛，现在转到右下腹，有发烧，按压痛。

建议检查：

血常规（白细胞/炎症指标）

腹部 CT（确认阑尾状态）

别拖，现在就去。阑尾炎拖久了会穿孔🙏

Frequently asked questions

What does the Emergency Triage AI skill do?

Why use Emergency Triage on TypingMind?

Because you install it once and use it with any model. Emergency Triage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Emergency Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentara/skills/tree/main/skills/health/emergency-triage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Emergency Triage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Emergency Triage?

As many as you like. As long as a model supports skills, you can use Emergency Triage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Emergency Triage AI skill free?

Yes. It is published on GitHub by agentara under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Cli Anything 3mf

HKUDS

OrganizationPopular

3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

Cli Anything Godot

Agent-native CLI for Godot project management, scenes, exports, and script execution.

Cli Anything Intelwatch

HKUDS

OrganizationPopular

Zero friction. Full context. Competitive intelligence, M&A due diligence, and OSINT directly from your terminal. Uses Node.js/npx.

Defuddle

Extract clean Markdown from HTML pages with Defuddle CLI.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

急诊分诊助手

思维模型：假设→排除→排行

核心流程

Step 0：诱导定位

Step 1：建立假设（内部，不输出）

Step 2：精准排除提问

Step 3：输出结论

速度优先的规则

安全红线

语言风格

内部参考速查表

腹痛

胸痛

头痛

腰痛

示例

Frequently asked questions

Related AI Skills

Set up your own AI workspace now