skills.rest
johnsonice
johnsoniceCOMMUNITY
Explore all skills by this author →
GitHub

process_resume_skill

Extract candidate name, gender, nationality, and URR status from resume PDFs into CSV.

Updated Oct 8, 2024
Search Tags:#recruitment#PDF extraction#Gemini AI#diversity#HR automation#candidate screening#resume parsing
One-click install
npx skills add https://github.com/johnsonice/Fund_Process_Automation --skill process-resume-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: process_resume_skill
Source: https://github.com/johnsonice/Fund_Process_Automation/tree/main/.claude/skills/process_resume_skill
Command: npx skills add https://github.com/johnsonice/Fund_Process_Automation --skill process-resume-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-generativeai, python-dotenv, tqdm, pandas, and includes scripts (resource) components.

What problem does it solves?

This Skill eliminates the tedious, manual process of reviewing candidate resumes to extract core information. It automates data entry and ensures consistent, structured data extraction from diverse PDF formats, including scanned documents, saving countless hours for HR and recruitment teams.

Core Features & Use Cases

  • AI-Powered Resume Processing: Leverages the Gemini API to directly process PDF resumes (both text-based and image-based) without prior text extraction.
  • Key Information Extraction: Accurately extracts essential candidate details: Name, Gender, Country of Nationality, and Under-Represented Region (URR) status.
  • Structured Data Output: Saves all extracted information into a clean, organized CSV file, ready for further analysis, filtering, or integration into other systems.
  • Diversity Identification: Automatically flags candidates from predefined Under-Represented Regions, aiding in diversity and inclusion initiatives.
  • Use Case: Process a folder containing hundreds of candidate resumes overnight. Wake up to a comprehensive CSV file detailing each candidate's key demographics, allowing your recruitment team to focus on qualitative assessments rather than data entry.

Quick Start

Process all PDF resumes in the /path/to/resume/folder and extract candidate name, gender, nationality, and URR status into a CSV file.

Frequently Asked Questions about process_resume_skill

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

FAQPage Schema
How do I extract candidate information from PDF resumes automatically?▼

Resume extraction uses AI to process PDF resumes—both text and scanned images—and automatically pulls Name, Gender, Nationality, and URR status into structured data without manual review or prior text conversion.

Can I process scanned resumes and text-based PDFs in the same batch?▼

Yes, this Skill handles both text-based and image-based scanned PDFs in a single batch operation, using Gemini AI to extract fields accurately from mixed resume formats and output results to CSV.

What setup do I need to run resume screening with the Gemini API?▼

You need a Google Gemini API key stored in a .env file (GOOGLE_API_KEY or GEMINI_API_KEY) and Python with dependencies: google-generativeai, pandas, tqdm, and python-dotenv for batch processing.

How does this identify candidates from under-represented regions?▼

The Skill flags candidates matching predefined Under-Represented Region criteria extracted from nationality data, automating diversity and inclusion tracking alongside standard demographic extraction into your CSV output.

What output format do I get after processing a folder of resumes?▼

Resume processing produces a clean CSV file with rows for each candidate and columns for Name, Gender, Nationality, URR status, and error handling flags, ready for HR system integration or filtering.

Related Skills

Explore More Data & Analytics Skills→
cdeistopenedcdeistopened
24

image-prompt-generator

Generate custom AI images with Google's Gemini API.

Community
Intermediate
johnsonicejohnsonice

generate_candidate_summary_skill

Generate a markdown diversity report from candidate_profile.csv.

Community
Intermediate
timothyfrasertimothyfraser
3

data-science-agent-loop

Automates data-science loops for batched Ollama Cloud tool calls with JSONL audits.

Community
Advanced
bomberoxenviosdosruedasbomberoxenviosdosruedas

agency-recruitment-specialist

Manage recruitment operations across Chinese hiring platforms with labor law compliance.

Community
Advanced