process-ema-data

Official

Convert EMA product PDFs into structured TSVs

Authormi-erasmusmc
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Parsing EMA Authorised Presentations PDFs is time-consuming and error-prone when done manually; this Skill automates extraction of packaging, strength, route, content, pack size, and product identifiers into machine-readable TSV files to support vocabulary mapping and downstream data workflows.

Core Features & Use Cases

  • Single-file parsing: Extract table fields from an Authorised Presentations PDF and write a parsed_data_<date>.tsv beside the source PDF.
  • Batch parsing: Prepare self-contained batch prompts for parallel subagents using prepare_parse_batch.py to parse multiple products reliably.
  • Data fetching & maintenance: Detect latest PDF dates, download updated PDFs from EMA, convert the medicines report to TSV, and generate ema-info metadata with a single command.
  • Use Case: A researcher rebuilding EMA→RxNorm mappings can fetch updates, parse new PDFs into per-product TSVs, and regenerate overview mappings without manual file inspection.

Quick Start

Run python3 .claude/skills/process-ema-data/scripts/fetch_ema_updates.py to download updated EMA presentations, generate ema-info metadata, and produce combined parsed TSV overviews.

Dependency Matrix

Required Modules

requestsbeautifulsoup4pandasopenpyxl

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: process-ema-data
Download link: https://github.com/mi-erasmusmc/ema-authorised-to-rxnorm-mappings/archive/main.zip#process-ema-data

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.