Extract text and per-page PNG images from PDFs using poppler-utils.
npx skills add https://github.com/gyy0592/claude-config --skill pdf-ingest
Please help me install this Agent Skill. Skill: pdf-ingest Source: https://github.com/gyy0592/claude-config/tree/main/skills/pdf-ingest Command: npx skills add https://github.com/gyy0592/claude-config --skill pdf-ingest
PDFs often lose critical visual information when converted to plain text: equations, subscripts, tables, and figures can be mangled or removed, making automated analysis unreliable. This skill preserves both a searchable text channel and faithful page images so downstream processing can quickly scan prose while verifying any visual content against an exact image.
Ingest paper.pdf at 150 DPI and return the path to the generated paper_temp directory along with the counts of text lines and page images.
High-intent search queries and answers about installing and using this skill.
To extract text and images without losing tables and equations, use a dual-channel approach that runs pdftotext for layout-preserved prose and pdftoppm to render page PNG files. This outputs a directory containing both text.txt and per-page images for visual verification.
PDF text extraction loses visual layout because plain text conversion strips equations, tables, and figures. Applying a dual-channel method preserves columns using pdftotext -layout while rendering exact page images with pdftoppm to retain visual fidelity for verification.
Yes, you need poppler-utils installed to extract text and page images. The workflow specifically requires the pdftotext and pdftoppm command-line tools to generate the text.txt file and render the per-page PNG images.
Yes, you can parse scanned-image PDFs even when text extraction returns empty. The dual-channel approach detects empty text but continues to render high-quality page images using pdftoppm, leaving the visual content fully usable for processing.
The best way to parse research papers and reports with figures is using a dual-channel extraction that produces searchable text.txt alongside per-page PNG images. This ensures formulas, tables, and figures are preserved for visual confirmation before analysis.
lyq-linExtract text from PDFs and create or merge PDF documents.
yuhaoliu7456Convert academic PDFs into structured Markdown documents using LLM vision.
mrlynnGenerate RAG pipelines with document ingestion, chunking, and retrieval architectures.
ekkus93Extract text from image files using Tesseract OCR.