Skills
.Work. You
Rest

extract-from-pdfs

Community

Turn PDFs into structured data for analysis.

Education & Research#workflow#pdf#Claude#metadata#pipeline#data-extraction
Authorbrunoasm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill turns large collections of scientific PDFs into structured data ready for meta-analyses, systematic reviews, and database creation, automating extraction, validation, enrichment, and export.

Core Features & Use Cases

  • Organize metadata from BibTeX, RIS, directories, or DOI lists
  • Filter papers by abstract (Claude or local models) to focus on relevant literature
  • Extract structured data from full PDFs using Claude's vision capabilities
  • Repair and validate outputs, enrich with external databases, and export to Python, R, CSV, Excel, or SQLite
  • Use case: conduct a rapid systematic review across hundreds of papers

Quick Start

Start by preparing your metadata and extraction schema, then run the 6-step pipeline as outlined in the repository workflow. Example files are provided in assets; to kick off the pipeline, run the steps in sequence: 01_organize_metadata.py, 02_filter_abstracts.py, 03_extract_from_pdfs.py, 04_repair_json.py, 05_validate_with_apis.py, and 06_export_database.py.

Dependency Matrix

Required Modules

anthropic>=0.40.0pybtex>=0.24.0rispy>=0.6.0json-repair>=0.25.0jsonschema>=4.20.0pandas>=2.0.0openpyxl>=3.1.0pyreadr>=0.5.0requests>=2.31.0

Components

scriptsreferencesassets

💻 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: extract-from-pdfs
Download link: https://github.com/brunoasm/my_claude_skills/archive/main.zip#extract-from-pdfs

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 471,000+ vetted skills library on demand.