skills.rest
markuskreitzer
markuskreitzerCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

scan-organizer

Extract text from scanned PDFs, classify document type, and move files into category folders.

1|Updated Mar 9, 2026
Search Tags:#ocr#pdf#document organization#openai-compatible api#llm classification#metadata sidecar#manifest undo
One-click install
npx skills add https://github.com/markuskreitzer/scan-organizer --skill scan-organizer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scan-organizer
Source: https://github.com/markuskreitzer/scan-organizer/tree/main
Command: npx skills add https://github.com/markuskreitzer/scan-organizer --skill scan-organizer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the manual work of opening scanned PDFs, figuring out what they are, extracting usable text, and reorganizing them into the right places.

Core Features & Use Cases

  • Dual extraction (Docling + vision OCR): Converts structured PDFs with Docling and falls back to vision OCR for pages with sparse text.
  • LLM-based classification: Assigns each document to one category (medical, financial, insurance, tax, legal, personal, household, other) and generates structured classification output.
  • Organized output with auditability: Moves PDFs into category subfolders and writes markdown plus JSON sidecar metadata, while recording each move in a manifest to support undo and reclassification.

Quick Start

Use the scan-organizer command to process your watch directory by running process so new PDFs get extracted, classified, and moved into categorized subfolders.

Frequently Asked Questions about scan-organizer

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

FAQPage Schema
How do I automatically categorize scanned PDFs into folders?▼

You can automatically categorize scanned PDFs by extracting text via Docling and vision OCR, then using an LLM to classify and move files into category subfolders. This removes the manual work of opening and sorting scans.

Can I use an OpenAI-compatible API to classify document types?▼

Yes, document classification uses an OpenAI-compatible chat completion endpoint to assign categories like medical, financial, or tax. The LLM receives extracted text and returns structured output for folder organization.

How does OCR work on scanned PDFs with sparse text?▼

OCR on scanned PDFs uses Docling for structured text extraction and falls back to vision OCR when page text is sparse. This dual extraction ensures usable text is recovered even from low-quality scans.

Can I undo moving PDFs into categorized folders?▼

Yes, you can undo PDF moves using the manifest file, which records each action with SHA-256 hashes. This manifest supports undoing moves and reclassifying documents if categories need adjustment.

What document categories are supported for scanned PDF organization?▼

Scanned PDF organization supports medical, financial, insurance, tax, legal, personal, household, and other categories. Each classified PDF is moved into its corresponding subfolder with markdown and JSON sidecar metadata.

Does this scanned PDF organizer work for small-office workflows?▼

Yes, this scanned PDF organizer fits small-office workflows and personal document management. It processes incoming scans by extracting text, classifying document type, and moving files for later retrieval.

Related Skills

Explore More Software Engineering Skills→
JigsawStackJigsawStack
4

ocr

Extract text and structured fields from images and scanned documents.

Official
Intermediate
TakMczkTakMczk
1

content-hash-cache-pattern

Cache file processing results using SHA-256 content hashes with JSON storage.

Community
Intermediate
afel6afel6

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate
Guard8-aiGuard8-ai
6

sear

Convert PDFs and DOCX files to searchable Markdown with OCR.

Official
Advanced