filter-csv-columns

Filter LinkedIn CSV exports into a 14-column recruiter screening dataset.

Updated Jan 26, 2026

Search Tags:#python #pandas #csv #data-transformation #data-cleaning #recruiting #profile-extraction

Ready to run

npx skills add https://github.com/gehtalexey/linkedin-enricher --skill filter-csv-columns

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: filter-csv-columns
Source: https://github.com/gehtalexey/linkedin-enricher/tree/main/.claude/skills/filter-csv-columns
Command: npx skills add https://github.com/gehtalexey/linkedin-enricher --skill filter-csv-columns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Filter an enriched LinkedIn CSV to keep only columns relevant for recruiter screening. Consolidates jobs, education, and skills into clean columns.

Core Features & Use Cases

Maintains a fixed schema of 14 columns including current position, past positions, education, and skills.
Produces a compact dataset suitable for candidate screening and reporting.
Works with CSV exports containing profiles, job histories, education, and skills to generate a consistent dataset.

Quick Start

Use the filter-csv-columns skill to process your input CSV and write the filtered output to a new CSV file.

Frequently Asked Questions about filter-csv-columns

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

FAQPage Schema

How do I filter a LinkedIn CSV export for recruiter screening?▼

Filtering an enriched LinkedIn CSV for recruiter screening involves retaining a fixed schema of 14 columns, consolidating job histories, education records, and skills into a clean dataset suitable for candidate evaluation and reporting.

Can I consolidate multiple job histories and education records into single CSV columns?▼

Consolidating multiple job histories and education records into single CSV columns is achieved by aggregating past positions and education entries, while computing current role details and deriving the current years in role using Python-based data processing.

What is the best way to extract only relevant candidate data from a large profile CSV?▼

Extracting relevant candidate data from a large profile CSV is best achieved by applying a fixed schema that retains 14 screening columns, producing a compact dataset that concatenates skills and aggregates past positions for consistent reporting.

Does this data-transformation method work with standard LinkedIn profile exports?▼

This data-transformation method works with standard CSV exports containing profile data, job histories, education records, and skills across multiple individuals, outputting a consistent 14-column dataset suitable for candidate screening.

How do I calculate current years in a role when cleaning a CSV file?▼

Calculating current years in a role when cleaning a CSV file involves using Python-based data processing to derive the duration from current position details, retaining it as one of the 14 essential screening columns.