Source: https://github.com/aipoch/medical-research-skills

When to Use

You have a paper converted from PDF to Markdown (including ## Page XX markers and image links) and need a figure-by-figure interpretation report.
You need to extract key variables, trends, comparisons, and conclusions primarily from charts/plots rather than from the main text.
You want to align images in a *-images/ folder with figure numbers (e.g., Figure 1A, Figure 2) using captions and in-text citations.
You need a standardized, UTF-8 Markdown output suitable for downstream summarization, data extraction, or knowledge base ingestion.
You must filter out non-figure images (e.g., scanned body text blocks) and interpret only chart-like content.

Key Features

Parses Markdown image links and locates the corresponding *-images/ directory (e.g., RateSOX2.md → RateSOX2-images/).
Opens every image in the images folder without skipping and classifies each as chart / table / schematic / flowchart / body-text block.
Builds an internal (non-exported) alignment list to map images to figure numbers using captions and body-text citations.
Interprets only chart-type images (and other figure-like visuals when required), excluding body-text blocks.
Produces a single structured “Image Interpretation” Markdown report per input file, saved to outputs/.
Enforces evidence-based interpretation: rely only on captions, body text, and visible image content; do not speculate.