symptom-checker-triage

Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a substitute for professional medical diagnosis.

3,891 stars

Best use case

symptom-checker-triage is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a substitute for professional medical diagnosis.

Teams using symptom-checker-triage should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/symptom-checker-triage/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aipoch-ai/symptom-checker-triage/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/symptom-checker-triage/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How symptom-checker-triage Compares

Feature / Agentsymptom-checker-triageStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a substitute for professional medical diagnosis.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Symptom Checker Triage

Analyzes symptom descriptions and suggests triage levels (Emergency / Urgent / Outpatient) based on red flag identification. Provides rationale and recommended next steps. For AI-assisted decision support only.

## Quick Check

```bash
python -m py_compile scripts/main.py
```

## Audit-Ready Commands

```bash
python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py "Chest pain, difficulty breathing, lasting 30 minutes"
python scripts/main.py "Headache, fever 38.5 degrees, vomiting" --verbose
```

## When to Use

- Triage a patient symptom description to Emergency, Urgent, or Outpatient level
- Identify red flag symptoms in a clinical or research context
- Generate structured triage output for documentation or downstream processing

## Workflow

1. Confirm the symptom description is provided as natural language text.
2. Validate that the request is a symptom triage task; stop early if not.
3. Run `scripts/main.py` with the symptom string or use `--interactive` mode.
4. Return a structured result with triage level, red flags, rationale, and disclaimer.
5. If execution fails or inputs are incomplete, switch to the Fallback Template below.

## Fallback Template

If `scripts/main.py` fails or required fields are missing, respond with:

```
FALLBACK REPORT
───────────────────────────────────────
Objective        : <triage goal>
Inputs Available : <symptom description provided>
Missing Inputs   : <list exactly what is missing>
Partial Result   : <any triage assessment that can be made safely>
Blocked Steps    : <what could not be completed and why>
Disclaimer       : This is AI-assisted advice only. Seek professional medical care.
Next Steps       : <minimum info needed to complete>
───────────────────────────────────────
```

## Stress-Case Output Checklist

For complex multi-constraint requests, always include these sections explicitly:

- **Assumptions**: symptom keywords matched, confidence threshold applied
- **Constraints**: rule-based engine only; no differential diagnosis
- **Risks**: false positives and false negatives are possible; always defer to clinician
- **Unresolved Items**: ambiguous symptoms requiring clarification

## CLI Usage

```bash
# Direct symptom input
python scripts/main.py "Chest pain, radiating to left arm, sweating"

# Interactive mode
python scripts/main.py --interactive

# Verbose output
python scripts/main.py "Headache, fever" --verbose

# JSON output
python scripts/main.py "Abdominal pain, right lower quadrant tenderness" --json
```

## Output Format

```json
{
  "triage_level": "emergency|urgent|outpatient",
  "confidence": 0.85,
  "red_flags": ["Chest pain", "Difficulty breathing"],
  "reason": "Chest pain with difficulty breathing may indicate myocardial infarction or pulmonary embolism",
  "recommendation": "Go to emergency department immediately",
  "department": "Emergency/Cardiology",
  "warning": "This is AI-assisted advice and cannot replace professional medical diagnosis"
}
```

## Triage Levels

| Level | Description | Action |
|---|---|---|
| emergency | Life-threatening red flags present | Call emergency services or go to ED immediately |
| urgent | Serious but not immediately fatal | Seek care within 2–4 hours |
| outpatient | Non-urgent | Schedule outpatient appointment |

## Red Flag Categories

→ Full red flags reference: [references/red_flags.md](references/red_flags.md)

Key categories: Cardiovascular, Respiratory, Neurological, Gastrointestinal, Trauma/Poisoning, Obstetric.

## Disclaimer

> **Important**: This tool provides AI-assisted triage suggestions only. It **cannot replace professional medical diagnosis**. If in doubt, seek medical care immediately. Call emergency services in life-threatening situations.

## Input Validation

This skill accepts: natural language symptom descriptions in English or Chinese for triage level suggestion.

If the request does not involve symptom triage — for example, asking to diagnose a specific disease, prescribe medication, interpret lab results, or perform general medical Q&A — do not proceed. Instead respond:

> "`symptom-checker-triage` is designed to suggest triage levels based on symptom red flags. Your request appears to be outside this scope. Please provide a symptom description, or use a more appropriate tool. This tool does not provide diagnoses or treatment recommendations."

## Error Handling

- If no symptom description is provided, request it explicitly.
- If the task goes outside documented scope (diagnosis, prescription), stop immediately.
- If `scripts/main.py` fails, use the Fallback Template above.
- Do not fabricate triage levels, red flag matches, or medical advice.

## Output Requirements

Every final response must include:

1. **Objective** — what symptom set was triaged
2. **Inputs Received** — symptom description used
3. **Assumptions** — keyword matching applied, confidence threshold
4. **Triage Result** — level, red flags identified, rationale
5. **Risks and Limits** — AI-only, not a diagnosis, false positive/negative risk
6. **Next Checks** — always recommend professional medical evaluation

## Dependencies

- Python 3.8+
- No third-party dependencies (rule-based engine, standard library only)

Related Skills

email-triager

3891
from openclaw/skills

Triage, categorize, and draft responses to emails. Sorts by urgency, flags action items, and generates context-aware reply drafts.

Workflow & Productivity

time-checker

3891
from openclaw/skills

Check accurate current time, date, and timezone information for any location worldwide using time.is. Use when the user asks "what time is it in X", "current time in Y", or needs to verify timezone offsets.

General Utilities

cyber-kev-triage

3891
from openclaw/skills

Prioritize vulnerability remediation using KEV-style exploitation context plus asset criticality. Use for CVE triage, patch order decisions, and remediation reporting.

Security

paper-reference-checker

3891
from openclaw/skills

This skill should be used when the user asks to "check paper citations", "verify references", "detect fake citations", "validate bibliography", "check if papers exist", "查文献真伪", "检查论文引用", "验证参考文献", "识别虚假引用", or uploads a PDF/Overleaf document and wants to verify whether the cited papers genuinely exist. Provides systematic verification of academic references against Google Scholar, CNKI, arXiv, and other academic databases to detect AI-hallucinated or fabricated citations.

agent-portability-checker

3891
from openclaw/skills

Audit agent skills for platform lock-in and cross-agent compatibility. Use when checking if a skill is portable, making a skill work across multiple agents (OpenClaw, Claude Code, Codex, etc.), fixing hardcoded paths, or preparing a skill for multi-platform distribution. Checks for hardcoded platform paths, missing env var support, and platform-specific dependencies.

gmail-checker

3891
from openclaw/skills

Check Gmail for unread inbox emails, filtered by priority. Use when asked to check emails, check inbox, email digest, email summary, or "any new mail". Outputs a brief list sorted by priority (HIGH/MEDIUM/LOW). Skips marketing, promotions, social, and update categories. Configurable via gmail-config.json.

hna-666-flight-checker

3891
from openclaw/skills

查询海南航空 666Plus 权益可往返航班,自动遍历指定目的地

SKILL: stock-checker

3891
from openclaw/skills

## Description

openclaw-triage

3891
from openclaw/skills

No description provided.

minimax-plan-checker

3891
from openclaw/skills

获取 MiniMax 平台的套餐信息,包括套餐名称、额度、当前使用情况。当用户询问 MiniMax 套餐、额度使用情况、API 调用量、计费信息时使用此技能。

email-triage

3891
from openclaw/skills

AI-powered email triage with calendar sync and response drafting

vibe-coding-checker

3891
from openclaw/skills

描述一个功能或项目,AI 快速评估用 Cursor/Windsurf/Bolt 等 AI 编程工具能否独立实现, 给出可行性判断、推荐工具、拆解路径和风险提示。