probe-education

Diagnose education section extraction failures in resume PDFs across routing, chunking, and field heuristics.

8|Updated May 29, 2026
One-click install
npx skills add https://github.com/offlinecv/OfflineCV --skill probe-education
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: probe-education
Source: https://github.com/offlinecv/OfflineCV/tree/main/.claude/skills/probe-education
Command: npx skills add https://github.com/offlinecv/OfflineCV --skill probe-education

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This tool identifies why specific education sections in a resume PDF fail to parse correctly, pinpointing whether the issue lies in header routing, chunking, or field extraction.

Core Features & Use Cases

  • Layered Diagnostics: Isolates failures between section routing, chunking logic, and field-specific heuristics.
  • Oracle-based Verification: Uses an independent header-recognition oracle to flag rejected headers and potential under-segmentation.
  • Use Case: When a user reports that their degree or institution is missing from the parsed output, this tool reveals exactly which regex or heuristic rule caused the drop.

Quick Start

Run the probe-education skill by providing the absolute path to the resume PDF in the environment variable RL_EDUCATION_PDF while executing the vitest harness.

Frequently Asked Questions about probe-education

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

FAQPage Schema
Why does my resume PDF parser miss degree or institution names in the education section?

Resume PDF parsing misses education entries when section header routing fails, chunking logic fragments entries, or field heuristics reject valid formatting. This Skill isolates the exact failing layer, identifying whether a specific regex or heuristic rule caused the degree or institution drop.

How do I debug resume PDF education extraction failures step by step?

Debug resume PDF education extraction by running the probe via the vitest harness with the absolute PDF path set in the RL_EDUCATION_PDF environment variable. The tool executes layered diagnostics across routing, chunking, and field heuristics to pinpoint the extraction failure.

What causes collapsed education entries in PDF resume parsing?

Collapsed education entries in PDF resume parsing occur due to formatting inconsistencies that trigger under-segmentation during chunking. The Skill uses an independent header-recognition oracle to flag rejected headers and detect when formatting variations cause multiple entries to merge.

Can I run resume parsing diagnostics locally to ensure PII safety?

Yes, the Skill operates entirely local-only to satisfy PII-safe debugging requirements. You execute the vitest harness locally with the resume PDF, ensuring no sensitive personally identifiable information leaves your environment during education parsing diagnostics.

How do I report automated issues found during resume education parsing?

The Skill features integrated GitHub tooling for automated issue reporting. After diagnosing education extraction failures, it generates actionable reports detailing the exact regex or heuristic rule responsible, ready for submission to your repository.

What is the best way to diagnose missed education headers in resume PDFs?

The best way to diagnose missed education headers is using an oracle-based verification approach. The Skill employs an independent header-recognition oracle to flag rejected headers and identify under-segmentation, isolating failures between section routing and field extraction layers.