via54medit

Route clinical questions into ranked evidence packages from multiple literature sources.

1|Updated Jun 13, 2026
One-click install
npx skills add https://github.com/veawho/via54Skills --skill via54medit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: via54medit
Source: https://github.com/veawho/via54Skills/tree/main/via54medit
Command: npx skills add https://github.com/veawho/via54Skills --skill via54medit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps developers and medical researchers turn natural-language clinical questions into structured, ranked evidence packages instead of manually searching and combining multiple literature databases.

Core Features & Use Cases

  • EBM Question Classification: Classify treatment, diagnosis, prognosis, etiology, prevention, and economic questions, then extract Population, Intervention, Comparison, and Outcome elements.
  • Multi-Source Literature Routing: Coordinate concurrent searches across PubMed, OpenAlex, Semantic Scholar, and the Anta Afu RAG source, with deduplication, enrichment, and four-tier ranking.
  • MCP and Systematic Review Support: Work with the ask, search, list, and persist_qa tools while preparing evidence for systematic reviews, meta-analyses, full-text screening, and knowledge-base persistence.
  • Use Case: For a question about SGLT2 inhibitors and heart-failure outcomes, route the query, assemble relevant studies, enrich them with citation and MeSH data, and return a ranked evidence package.

Quick Start

Ask the agent to use via54medit to classify a clinical question, extract its PICO elements, search all available literature sources, and return a ranked evidence package.

Frequently Asked Questions about via54medit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract PICO elements from a natural-language clinical question for a systematic review?

Evidence-based medicine question classification extracts Population, Intervention, Comparison, and Outcome elements from natural-language clinical questions to prepare structured queries for systematic-review literature searches.

What's the best way to search multiple medical literature databases and deduplicate the results?

Multi-source literature routing concurrently searches PubMed, OpenAlex, Semantic Scholar, and Anta Afu RAG, then applies deduplication and MeSH enrichment to assemble a consolidated evidence package.

How does four-tier ranking work for evidence-based medicine search results?

Four-tier ranking evaluates retrieved medical literature using FWCI, TLDR, and MeSH enrichment data to prioritize stronger evidence for clinical questions and systematic-review preparation.

Can I use MCP tools to classify clinical questions and persist literature search Q&A?

Yes, the ask, search, list, and persist_qa MCP tools classify clinical questions, coordinate multi-source retrieval, and optionally persist Q&A sessions into a knowledge base.

Does this approach support both treatment and prognosis question types for medical literature routing?

Evidence-based medicine question classification supports treatment, diagnosis, prognosis, etiology, prevention, and economic question types before routing them to ranked medical literature evidence packages.

Do I need to manually query each database separately for systematic review preparation?

No, coordinated source dispatch automatically routes queries across PubMed, OpenAlex, Semantic Scholar, and Anta Afu RAG, eliminating manual multi-database searches for systematic-review preparation.