pdf-dft-extractor

Extract DFT coordinates from PDFs and generate Gaussian input files.

52|11|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/InternScience/ChemClaw --skill pdf-dft-extractor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-dft-extractor
Source: https://github.com/InternScience/ChemClaw/tree/main/skills/pdf-dft-extractor
Command: npx skills add https://github.com/InternScience/ChemClaw --skill pdf-dft-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mineru-pdf-converter, pdf_to_markdown.

What problem does it solve?

This skill addresses the manual bottleneck of converting molecular coordinates embedded in PDF documents into ready-to-run Gaussian input files (gjf). It specifically targets supplementary materials and other PDFs that contain computed coordinates, enabling batch extraction and organized output folders per PDF.

Core Features & Use Cases

  • Automatically convert PDFs to structured data via MinerU to access coordinates
  • Extract Cartesian coordinates for one or more molecules from each document
  • Generate Gaussian input files with sane defaults and per-molecule naming
  • Batch-process entire directories, producing isolated output folders for each PDF

Quick Start

Run the extractor on a single PDF to generate gjf files and a summary in the output folder.

Frequently Asked Questions about pdf-dft-extractor

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

FAQPage Schema
How do I extract DFT coordinates from a PDF for Gaussian calculations?

To extract DFT coordinates from a PDF for Gaussian calculations, the skill converts the document to structured Markdown via MinerU, identifies the molecular coordinates, and generates ready-to-run Gaussian input files (gjf) with sanitized per-molecule naming.

Can I batch process multiple PDFs to generate Gaussian input files?

Yes, you can batch process multiple PDFs to generate Gaussian input files. The skill supports batch processing entire directories and automatically creates isolated output folders for each PDF to keep the extracted gjf files organized.

What is the best way to convert supplementary material PDFs into gjf files?

The best way to convert supplementary material PDFs into gjf files is using an automated extraction pipeline. This skill specifically targets supplementary materials, parsing the converted Markdown to enforce coordinate extraction and robust gjf generation.

Do I need MinerU to extract Cartesian coordinates from PDF documents?

Yes, you need MinerU to extract Cartesian coordinates from PDF documents. The skill relies on the MinerU PDF converter to transform the PDF into Markdown, which is then parsed to isolate the molecular coordinates for downstream quantum chemistry calculations.

Why does my extracted Gaussian input file have a modified molecule name?

Your extracted Gaussian input file has a modified molecule name because the skill enforces file-name sanitization. This process ensures the generated gjf files have valid, robust naming conventions required for downstream quantum chemistry calculations.