ocr-document-processor

dkyazzentwatwa/chatgpt-skills

Extract text and structure from scans, images, and PDFs using OCR with specialized parsers for receipts and business cards.

Source View on skills.sh

What is ocr-document-processor?

Recovers text and structure from scanned documents, images, and image-based PDFs. Use this when you need OCR, searchable PDF export, table extraction, or parsing of receipts and business cards.

OCR on images and scanned PDFs
Generate searchable PDF exports
Extract structured data to text, markdown, JSON, or HTML
Parse tables from scanned material
Parse receipts and business cards with specialized helpers

How to install ocr-document-processor

npx skills add https://github.com/dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor

Prerequisites

Python environment with OCR dependencies installed
Input images or scanned PDFs in common formats (PNG, JPG, PDF)

Claude Code

Cursor

Windsurf

Cline

How to use ocr-document-processor

1.Determine whether you need plain OCR, structured extraction, or specialized parsing (receipt/business card)
2.Preprocess noisy inputs if they have skew, blur, or shadows
3.Use scripts/ocr_processor.py for general OCR tasks
4.Use scripts/business_card_scanner.py or scripts/receipt_scanner.py for specialized document types
5.Return confidence caveats when source quality is low, rotated, handwritten, or multilingual

Use cases

Good for

Converting scanned invoices or receipts into searchable, structured data
Extracting contact information from business card images
Creating searchable PDFs from image-based document scans
Recovering text from low-quality or rotated scans with preprocessing
Extracting tabular data from scanned spreadsheets or forms

Who it's for

Document processing specialists
Administrative staff handling paper records
Developers building document digitization pipelines
Anyone processing receipts, invoices, or business cards at scale

ocr-document-processor FAQ

Should I use this for digital PDFs?

No. Route non-scanned digital PDFs to document-converter-suite instead. This skill is optimized for image-based and scanned documents.

How do I handle low-quality or rotated scans?

Preprocess noisy inputs before extraction when skew, blur, or shadows are present. Always return confidence caveats for low-quality sources.

What output formats are supported?

Structured extraction to text, markdown, JSON, or HTML, plus searchable PDF export.

Can this handle multilingual documents?

Yes, but prefer explicit language selection when accuracy matters for best results.

Are there specialized parsers for specific document types?

Yes. Use business_card_scanner.py for business cards and receipt_scanner.py for receipts.

Full instructions (SKILL.md)

Source of truth, from dkyazzentwatwa/chatgpt-skills.

name: ocr-document-processor description: Extract text and structure from scans, images, and scanned PDFs. Use for OCR, searchable PDFs, table extraction, receipt parsing, and business card parsing.

OCR Document Processor

Handle OCR-heavy inputs where text must be recovered from images or scanned pages.

Use This For

OCR on images and scanned PDFs
Searchable PDF export
Structured extraction to text, markdown, JSON, or HTML
Table extraction from scanned material
Receipt parsing and business card parsing

Workflow

Decide whether plain OCR, structured extraction, or document-specific parsing is needed.
Preprocess noisy inputs before extraction when skew, blur, or shadows are present.
Use scripts/ocr_processor.py for core OCR tasks.
Use the focused helpers when the input is specialized:
- scripts/business_card_scanner.py
- scripts/receipt_scanner.py
Return confidence caveats when the source is low quality, rotated, handwritten, or multilingual.

Guardrails

Prefer explicit language selection when accuracy matters.
Do not claim fields are exact when OCR confidence is weak.
Route non-scanned digital PDFs to document-converter-suite instead of OCR by default.

Related skills

More from dkyazzentwatwa/chatgpt-skills and the wider catalog.

crypto-ta-analyzer

dkyazzentwatwa/chatgpt-skills

Multi-indicator technical analysis for crypto and market OHLCV data with trend, momentum, volume, and divergence signals.

1.5k installsAudited

text-summarizer

dkyazzentwatwa/chatgpt-skills

Generate extractive summaries from long text documents. Control summary length, extract key sentences, and process multiple documents.

699 installsAudited