generate-candidate-summary-skill

johnsonice's avatarfrom johnsonice

Generate a markdown summary report from candidate_profile.csv with statistics and insights

⭐0stars🔀0forks📁View on GitHub🕐Updated Dec 8, 2025
[Hiring Operations]

When & Why to Use This Skill

This Claude skill automates the generation of comprehensive candidate summary reports from CSV data. It provides recruitment teams with instant insights into applicant demographics, including gender distribution, nationality diversity, and Under-Represented Region (URR) representation, all formatted in a professional Markdown report for easy sharing and documentation.

Use Cases

  • DEI Reporting: Automatically calculate and visualize gender and URR statistics to monitor and improve diversity initiatives within the hiring pipeline.
  • Talent Pool Analysis: Generate high-level summaries of candidate nationalities and backgrounds to help hiring managers understand geographic diversity and sourcing effectiveness.
  • Recruitment Workflow Automation: Seamlessly transform raw candidate profile data into structured insights and tables, eliminating manual data entry and spreadsheet formatting for HR teams.
namegenerate_candidate_summary_skill
descriptionGenerate a markdown summary report from candidate_profile.csv with statistics and insights

Generate Candidate Summary Report

This skill generates a comprehensive markdown summary report analyzing candidate profile data with statistics on gender distribution, URR representation, and nationality diversity.

What it does:

  • Reads candidate profile CSV data
  • Calculates comprehensive statistics (gender, URR, nationality)
  • Generates formatted markdown report with tables and insights
  • Identifies URR countries represented in the candidate pool

Usage:

Basic Usage

Run the summary generation script with default settings:

python .claude/skills/generate_candidate_summary_skill/generate_summary.py

This uses default paths:

  • Input: /data/home/xiong/dev/Fund_Process_Automation/candidate_profile.csv
  • Output: /data/home/xiong/dev/Fund_Process_Automation/summary.md

With Custom Paths

Specify custom input and output files:

python .claude/skills/generate_candidate_summary_skill/generate_summary.py \
  --csv_file /path/to/candidate_profile.csv \
  --output_file /path/to/summary.md

Command-line Arguments:

  • --csv_file: Path to input CSV file (default: candidate_profile.csv in project root)
  • --output_file: Path to output markdown file (default: summary.md in project root)

Input Requirements:

Expected Input File:

  • Path: /data/home/xiong/dev/Fund_Process_Automation/candidate_profile.csv
  • Format: CSV file with the following columns:
    • Name: Candidate's full name
    • Gender: Male/Female/Unknown
    • Country of Nationality: Country name
    • URR: "yes" or "no"

Note: This file is typically generated by the process_resume_skill.

Output:

Generated File:

  • Path: /data/home/xiong/dev/Fund_Process_Automation/summary.md
  • Format: Markdown document

Report Contents:

  1. Overview Section

    • Total number of candidates analyzed

  2. Summary Statistics Tables

    • Gender distribution (Male/Female/Unknown) with counts and percentages
    • URR vs Non-URR distribution with percentages
    • Top 10 nationalities with counts and URR status

  3. Key Insights

    • Gender balance analysis
    • URR representation percentage
    • Geographic diversity metrics
    • Most common nationality

  4. URR Countries List

    • All URR countries represented in the pool
    • Candidate count per URR country

Example Output Structure:

# Candidate Profile Summary

## Overview
This analysis covers X candidate resumes...

## Summary Statistics

### Gender Distribution
| Gender | Count | Percentage |
|--------|-------|------------|
| Male   | X     | XX.X%      |
| Female | X     | XX.X%      |

### Under-Represented Region (URR) Distribution
| URR Status | Count | Percentage |
|------------|-------|------------|
| URR (Yes)  | X     | XX.X%      |

### Top Nationalities Represented
| Country | Count | URR Status |
|---------|-------|------------|
...

## Key Insights
1. Gender Balance: ...
2. URR Representation: ...
3. Geographic Diversity: ...

## URR Countries Identified
- Country: X candidate(s)
...

Dependencies:

  • Python 3.x
  • pandas library (pip install pandas)

Configuration:

Default file paths (can be overridden with command-line arguments):

  • Input: /data/home/xiong/dev/Fund_Process_Automation/candidate_profile.csv
  • Output: /data/home/xiong/dev/Fund_Process_Automation/summary.md

Error Handling:

The script includes comprehensive error handling:

  • Validates input CSV file exists before processing
  • Checks for required columns (Gender, URR, Country of Nationality)
  • Ensures CSV is not empty
  • Creates output directory if it doesn't exist
  • Provides clear error messages via logging

Console Output:

When successful, displays:

==================================================
SUMMARY REPORT GENERATED
==================================================
Output file: /path/to/summary.md
Total candidates: X
Male: X, Female: X, Unknown: X
URR: X, Non-URR: X
==================================================

Key Features:

  • Flexible paths: Use command-line arguments to specify custom input/output locations
  • Robust validation: Checks file existence, column presence, and data integrity
  • Automatic directory creation: Creates output directories if they don't exist
  • Comprehensive logging: Provides detailed information about processing steps
  • Dynamic date: Report includes current generation date
  • Error handling: Graceful failure with informative error messages