Resume Information Processor

About

This skill automates the tedious task of manual data entry for recruitment by leveraging the Gemini API to analyze candidate resumes. It handles both text-based and scanned PDFs, accurately extracting key demographic information and identifying applicants from under-represented regions (URR) based on pre-defined global lists. By providing structured CSV outputs and summary statistics, it helps hiring teams streamline their screening process and maintain data-driven insights into candidate diversity.

Key Features

• Automates batch processing of resumes into structured CSV format.
• Identifies candidates from Under-Represented Regions based on global geographical data.
• Extracts name, gender, nationality, and URR status using Gemini 2.0 Flash.
• Generates demographic statistics and gender distribution reports.
• Supports both text-based and image-based (scanned) PDF documents.
• 0 GitHub stars

Use Cases

• Analyzing applicant diversity by tracking Under-Represented Region (URR) metrics.
• Extracting structured candidate data for large-scale hiring pipeline reviews.
• Automating the population of recruitment databases from bulk PDF uploads.