pre-filter-candidates

Filter candidate records from enriched CSV by past candidates and blacklisted companies.

Updated Jan 26, 2026

Search Tags:#csv #filters #candidates #data-cleaning #pre-filter #blacklist #past-candidates

Ready to run

npx skills add https://github.com/gehtalexey/linkedin-enricher --skill pre-filter-candidates

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pre-filter candidates from enriched CSV before AI screening to remove past candidates, apply a blacklist, and apply optional filters.

Core Features & Use Cases

Past-candidates removal: excludes candidates already processed for the client by matching first_name + last_name in past_candidates.csv.
Blacklist filtering: excludes candidates whose current_company matches any blacklisted company.
Optional filters: optional filters for not-relevant companies, target companies, top-university flagging, and job-hopper detection.
Output: produces filtered_candidates.csv and a summary of exclusions per rule.

Quick Start

Run the pre-filter-candidates skill on the input enriched CSV and client folder to produce filtered_candidates.csv.

Frequently Asked Questions about pre-filter-candidates

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

FAQPage Schema

How do I filter past candidates and blacklisted companies from a CSV before AI screening?▼

To pre-filter candidates from an enriched CSV, you run a workflow that matches first and last names against a past_candidates.csv file and excludes current companies found in a blacklist. This produces a clean filtered_candidates.csv subset ready for scoring.

What CSV data cleaning steps are needed to remove duplicate job applicants from a pipeline?▼

CSV data cleaning for duplicate applicant removal involves matching candidate first_name and last_name fields against historical records in a past_candidates.csv file. This pre-filtering process ensures previously processed individuals are excluded from the active candidate pipeline.

Can I flag top-university graduates and detect job hoppers during CSV candidate filtering?▼

Yes, candidate CSV filtering can apply optional rules to flag top-university graduates and detect job hoppers. These pre-filter checks run alongside blacklist matching and not-relevant company exclusion before generating the final output file.

Does the pre-filter candidate workflow require any specific dependencies or external components?▼

No specific dependencies or external components are required to run the pre-filter candidate workflow. It operates directly on an enriched candidate CSV and a client folder containing filter lists to output the filtered results.

What is the best way to exclude not-relevant and target companies from candidate records?▼

The best way to exclude not-relevant or target companies from candidate records is applying optional blacklist filters during the CSV pre-filtering stage. This removes unwanted employer matches and outputs a summary of all exclusions per rule.

Why does my candidate CSV filtering not remove all past applicants from the pipeline?▼

Candidate CSV filtering fails to remove past applicants when first_name and last_name fields do not exactly match records in past_candidates.csv. Accurate pre-filtering requires clean, consistently formatted name columns across both input files.