Medical Master Router
Paste the following prompt into your AI chat to install this skill:
Please install @user_b3374e25/medical-master-router according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Medical questions often span diagnosis, guidelines, drug safety, genomics, imaging, and report interpretation. If an agent gives a generic answer immediately, it may miss entity normalization and specialized downstream skills, making the response less reliable.
How It Works
Medical Master Router routes requests to narrower medical skills before producing a general answer. It follows several key steps:
- Intent classification: detect the user’s real goal and map it to domains such as clinical care, medication safety, precision oncology, single-cell analysis, CRISPR, and imaging pathology.
- Entity normalization: standardize
disease names,generic drug names,gene symbols,cancer stage/histology, and data formats such asFASTQ,VCF,h5ad, andDICOMbefore retrieval. - Precise routing: prefer the most specific primary and companion skills; use composite routing for multi-domain questions; fall back to
bio-*,clinical-*, ortooluniverse-*families when no exact match is obvious. - Report-first handling: for lab reports, checkup reports, or imaging reports, first detect the report type, then extract OCR/content, key findings, abnormal items, and missing context before interpretation.
Boundaries
The skill is intended for informational and decision-support purposes, not as a doctor or a substitute for professional care. It should distinguish general medical information from patient-specific advice, avoid inventing clinical facts, surface missing inputs when needed, and prioritize escalation guidance for emergencies or mental-health crises.
Use Cases
- After receiving a checkup-report screenshot, identify the report type and abnormal lab items, then suggest follow-up tests based on thresholds.
- When evaluating first-line therapy for EGFR-mutant lung adenocarcinoma, route across precision oncology, guideline evidence, and trial eligibility criteria.
- When analyzing TCR repertoire data, invoke immune-repertoire and T-cell exhaustion skills to infer immune-status signals.
- When reading a prescription or medication photo, extract drug, dose, contraindication, and interaction details before answering medication-safety questions.
Best For
- Engineers building medical AI agent applications that must dispatch clinical and bioinformatics queries to specialized skills
- Medical data engineers working with report screenshots or PDFs and needing OCR plus structured extraction first
- Research assistants in oncology, drug safety, or genomics who need evidence retrieval and downstream analysis routing
- Developers building Cline, OpenClaw, or similar AI assistant plugins and needing checks for installed downstream skills
Related Skills
Local workflow memory with matching and SOP updates.
An OpenClaw live streaming executor that initializes TRTC streaming, starts a real-time dashboard, generates viewer URLs, and continuously reports live events.
Breaks down physical supply chains for super-trends to identify second- and third-layer bottlenecks, runs valuation and reverse checks, and maintains trackable reports.
A token-saving compression mode for Chinese LLMs with lite, full, ultra, and classical tiers, preserving code and technical terms while handling edge cases.