extraction-debugger

Diagnose PDF extraction to Kotlin pipeline failures via queue and logs.

1|Updated Dec 21, 2025
One-click install
npx skills add https://github.com/carnaticlabs/Sangeetha-Grantha --skill extraction-debugger
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: extraction-debugger
Source: https://github.com/carnaticlabs/Sangeetha-Grantha/tree/main/.agent/skills/extraction-debugger
Command: npx skills add https://github.com/carnaticlabs/Sangeetha-Grantha --skill extraction-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps diagnose and resolve issues within the PDF extraction to Kotlin processing pipeline, ensuring data is correctly processed and matched.

Core Features & Use Cases

  • Queue Monitoring: Check the status of extraction jobs, identify failures, and find stuck processes.
  • Log Analysis: Review worker logs to pinpoint errors during extraction.
  • Matching Diagnostics: Analyze unmatched extractions and calculate match rates for specific sources.
  • Output Comparison: Compare raw Python extractor output with persisted Kotlin results.
  • Use Case: If new PDF documents are not appearing in the system after processing, use this Skill to check the extraction queue for failures, examine worker logs for errors, and compare the Python output with the Kotlin database entries to find discrepancies.

Quick Start

Use the extraction-debugger skill to check the status of the extraction queue for failed jobs.

Frequently Asked Questions about extraction-debugger

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

FAQPage Schema
How do I debug extraction pipeline failures when PDF documents are not appearing in the system?

To debug extraction pipeline failures, check the extraction queue status for failed jobs, examine worker logs for errors, and compare Python extractor output with Kotlin database results to locate discrepancies.

Why does my extraction pipeline have a low matching rate between Python output and Kotlin results?

Low matching rates occur when Kotlin processor results diverge from Python extractor output; diagnose by analyzing unmatched extractions and calculating match rates for specific sources using SQL queries.

How do I check the extraction queue for stuck or failed jobs in a Docker pipeline?

Check the extraction queue by running SQL queries to identify failed jobs and stuck processes, then review Docker worker logs to pinpoint errors encountered during the PDF extraction.

What's the best way to compare Python extractor output with persisted Kotlin database entries?

The best way to compare outputs is to retrieve raw Python extractor results and contrast them against persisted Kotlin database entries using SQL queries to identify mismatches or missing data.

Do I need SQL and bash to diagnose matching failures in the extraction pipeline?

Yes, diagnosing matching failures requires SQL queries to query database records and bash commands to access Docker worker logs for analyzing extraction and processing errors.

What to do when PDF extraction produces unexpected results in the Kotlin processing pipeline?

When PDF extraction produces unexpected results, review worker logs for extraction errors, verify queue status for failures, and compare raw Python output against Kotlin processor results to isolate the issue.