probe-skills

Name: probe-skills
Availability: InStock
Author: offlinecv

Diagnoses PDF résumé skills extraction failures via routin and header analysis.

8|Updated May 29, 2026

Search Tags:#debugging #pdf #heuristics #resume #extraction #parser

Ready to run

npx skills add https://github.com/offlinecv/OfflineCV --skill probe-skills

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: probe-skills
Source: https://github.com/offlinecv/OfflineCV/tree/main/.claude/skills/probe-skills
Command: npx skills add https://github.com/offlinecv/OfflineCV --skill probe-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill resolves issues where résumé skills sections are missing or incorrectly parsed due to PDF formatting, header recognition failures, or layout complexities.

Core Features & Use Cases

Diagnostic Routing: Identifies whether a skills section was dropped due to header recognition errors or extraction failures.
Failure Analysis: Provides detailed feedback on rejected headers, such as those with leading decorative glyphs or non-standard wording.
Use Case: When a candidate's skills are not appearing in the system, use this tool to determine if the parser failed to identify the skills header or if the text extraction layer failed to capture the content beneath it.

Quick Start

Run the probe-skills skill by executing the vitest command with the absolute path to the target resume PDF assigned to the RL_SKILLS_PDF environment variable.

Frequently Asked Questions about probe-skills

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

FAQPage Schema

Why are skills sections missing when parsing résumé PDFs?▼

Missing skills sections during résumé PDF parsing typically result from header recognition failures or layout-based text extraction errors. This diagnostic skill isolates whether the parser missed the header or failed to capture the content beneath it.

How do I debug PDF résumé parser heuristics for rejected headers?▼

Debug résumé PDF parser heuristics by running a vitest environment with the target PDF assigned to the RL_SKILLS_PDF environment variable. This executes parser heuristics against the file and reports rejected headers with detailed failure analysis.

What causes a résumé PDF parser to drop skills sections with decorative glyphs?▼

Decorative glyphs or non-standard wording in section headers cause the parser to reject the skills section. This tool identifies these header misrecognition failures and reports them so you can adjust extraction heuristics accordingly.

Do I need a local vitest environment to run résumé PDF extraction diagnostics?▼

Yes, a local vitest environment is required to execute parser heuristics against the target résumé PDF. The diagnostic relies on vitest to test section routing logic and text extraction performance for specific files.

How does résumé PDF section routing logic fail during text extraction?▼

Section routing logic fails when the parser misclassifies headers due to formatting complexities or decorative elements, preventing the text extraction layer from capturing the associated content. This skill analyzes routing to pinpoint the exact failure mode.

Can I verify if résumé PDF data loss is caused by header misrecognition or extraction failure?▼

Yes, you can verify the cause of résumé PDF data loss by running this diagnostic tool. It distinguishes between header misrecognition, where the parser drops the section entirely, and extraction failures, where the header is found but content is lost.