Skip to main content Skills Marketplace Descubre y explora habilidades de IA creadas por la comunidad.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Mostrar detalles del prompt Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill argentine-invoice-processing-systemEl comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.
¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.
Descargar Zip Descargando... Ocupaciones relacionadas SOC
Basado en la clasificación ocupacional SOC
Explorador de archivos
2 archivos name Argentine Invoice Processing System description Complete invoice processing system for Argentine utility bills with OCR, classification, and automated organization version 1.0.0 author Santiago Braida tags ["invoice-processing","document-automation","ocr","utilities","argentina","file-organization"] categories ["document-processing","automation"] prerequisites [".NET 9.0 Runtime","Tesseract OCR with Spanish support","macOS or Linux environment"] related_skills ["invoice-processing","ocr-troubleshooting","service-identification","date-extraction","testing-procedures","deployment-guide"]
Argentine Invoice Processing System
Overview
This skill enables automated processing, classification, and organization of Argentine utility invoices (electricity, water, gas, municipal services, etc.). The system extracts text from PDFs and images using OCR, identifies service providers, extracts dates, and organizes files into a structured year/month hierarchy with standardized naming.
What This Skill Does
OCR Processing : Extract text from PDFs, images (JPG, PNG) using TesseractService Classification : Identify service providers (AYSA, Edenor, Metrogas, ARBA, etc.)Date Extraction : Parse due dates from Spanish-language invoicesFile Naming : Apply consistent naming convention: {service}_{YYYY-MM-DD}_{payment}.extOrganization : Create year/month folder structure (e.g., 2025/03_marzo/)Parallel Processing : Handle multiple files concurrently
When to Use This Skill
Use this skill when you need to:
Process and organize utility invoices
Extract dates from Spanish-language documents
Classify Argentine service providers
Troubleshoot OCR issues with Spanish text
Deploy or maintain the invoice processing system
Add new service providers or rules
Test invoice processing functionality
Quick Start
Basic Usage
dotnet run --project FileContentRenamer/FileContentRenamer.csproj
dotnet run --project FileContentRenamer -- /path/to/invoices
Key Configuration
{
"AppConfig" : {
"BasePath" : "/Users/santibraida/Downloads/__comprobantes/servicios" ,
"FileExtensions" : [ ".pdf" , ".jpg" , ".png"
]
,
"TesseractLanguage"
:
"spa+eng"
,
"MaxDegreeOfParallelism"
:
4
}
}
Detailed Documentation This skill is organized into specialized sub-skills for different aspects of the system:
Core workflow and service provider directory. Start here for system overview.
Complete processing workflow
Service provider catalog (AYSA, Edenor, Metrogas, etc.)
File naming conventions
Folder organization structure
Configuration reference
When to use : Understanding the overall system, adding new providers, configuring the app
Diagnose and fix OCR issues with Tesseract.
Common OCR problems and solutions
Spanish character recognition
Image quality requirements
Performance optimization
Tesseract configuration
When to use : OCR producing garbled text, missing content, or slow performance
Detailed patterns for each service provider.
Provider-specific keywords and identifiers
Invoice characteristics and formats
Validation rules and amount ranges
Edge cases and conflicts
Seasonal patterns
When to use : Adding new providers, debugging misclassification, understanding provider specifics
Comprehensive date parsing patterns and validation.
All regex patterns with priority order
Argentine date format handling
OCR error correction for dates
Multiple date scenarios
Validation and edge cases
When to use : Date extraction issues, adding new date patterns, understanding parsing logic
Complete testing guide from unit tests to production validation.
Unit, integration, and E2E testing
Test data management
Manual testing procedures
Performance and regression testing
CI/CD integration
When to use : Writing tests, validating changes, testing new invoice types, quality assurance
Production deployment and maintenance handbook.
Installation and setup
Production configuration
Monitoring and health checks
Backup and recovery
Troubleshooting common issues
Security considerations
When to use : Deploying to production, setting up scheduled runs, maintenance, troubleshooting
Common Workflows
Adding a New Service Provider
Troubleshooting OCR Issues
Check ocr-troubleshooting.md for your specific issue
Verify Tesseract configuration and language packs
Test image quality requirements
Apply preprocessing if needed
Check logs for detailed error messages
Fixing Date Extraction
Review date-extraction.md for pattern priority
Check if date format is supported
Apply OCR error correction patterns
Add new regex pattern if needed
Validate with unit tests
Deploying to Production
Follow deployment-guide.md installation steps
Configure production settings
Set up monitoring and logging
Test with sample invoices
Schedule automated runs (cron/launchd)
Architecture Overview FileContentRenamer/
├── Program.cs # Entry point, configuration loading
├── Configuration/
│ └── ServiceConfiguration.cs # Dependency injection setup
├── Models/
│ ├── AppConfig.cs # Configuration model
│ └── NamingRule.cs # Service provider rules
└── Services/
├── FileService.cs # Main orchestrator
├── PdfProcessor.cs # PDF text extraction
├── ImageProcessor.cs # OCR with Tesseract
├── TextProcessor.cs # Plain text handling
├── DateExtractor.cs # Date parsing
├── FilenameGenerator.cs # Naming rules application
├── DirectoryOrganizer.cs # Folder structure creation
└── FileValidator.cs # File validation
Supported Service Providers Provider Type Code AYSA Water & Sanitation aysaEdenor Electricity edenorMetrogas Natural Gas metrogasMunicipality of Quilmes Municipal Taxes municipal_quilmesARBA Inmobiliario Property Tax arba_inmobiliarioARBA Automotor Vehicle Tax arba_automotorPersonal/Flow Mobile/Internet personalQuilmes High School School Tuition high_school_cuotaQuilmes High School School Lunch high_school_comedorGloria Domestic Service gloria
Key Features
Intelligent Date Extraction Handles multiple date formats with priority order:
Due date (abbreviated): Vto.:DD/MM/YYYY
Due date (full): vencimiento DD/MM/YYYY
Spanish format: DD de MONTH de YYYY
Generic: DD/MM/YYYY
OCR with Error Correction
Automatic correction of common OCR mistakes (O→0, I→1, S→5)
Support for Spanish characters (ñ, á, é, í, ó, ú)
Multi-language support (Spanish + English)
Flexible Organization Files organized into year/month structure:
servicios/
└── 2025/
├── 03_marzo/
│ └── aysa_2025-03-21_santander.pdf
└── 08_agosto/
└── gloria_2025-08-08_mercadopago.jpeg
Parallel Processing Configurable parallelism for faster processing of large batches while maintaining file safety with proper locking.
Configuration Reference
Key Settings Setting Description Default BasePathRoot directory to scan .FileExtensionsFile types to process [".pdf", ".jpg", ".png"]IncludeSubdirectoriesScan subdirectories trueTesseractLanguageOCR languages "spa+eng"MaxDegreeOfParallelismConcurrent files 4ForceReprocessAlreadyNamedReprocess named files false
Logging
Console: Real-time processing status
File: logs/app{YYYYMMDD}.log (daily rotation)
Log Levels
Information : Normal processing flowWarning : Skipped files, no content foundError : Processing failures, OCR errorsDebug : Detailed extraction and matching info
Performance Typical performance (4-core system):
PDF : ~1-2 seconds per fileImage (OCR) : ~3-5 seconds per fileLarge batch (100 files): ~5-8 minutes
Troubleshooting Quick Reference
Testing dotnet test FileContentRenamer.Tests/
Updates and Maintenance
Weekly : Review logs for errorsMonthly : Update service provider rules if neededQuarterly : Review and archive old invoicesYearly : Update dependencies and .NET runtime
Version History
v1.0.0 (2025-11-06): Initial skill documentation
Complete invoice processing system
Support for 10 service providers
OCR with Tesseract
Automated organization
Support
Related Technologies
.NET 9.0 : Application frameworkTesseract OCR : Text extraction from imagesSerilog : Structured loggingxUnit : Unit testing frameworkImageMagick : Image preprocessing (optional)
Best Practices
Always backup before processingTest with samples before bulk processingMonitor logs for errors and warningsKeep configuration in version control (except production secrets)Update skills documentation when adding features
Getting Help
Check the relevant detailed skill file for your issue
Review logs for error messages
Search existing GitHub issues
Create new issue with:
Sample invoice (redacted)
Log excerpt
Configuration used
Expected vs actual behavior
Start with invoice-processing.md for the complete system overview, then dive into specific skill files as needed.
