skills.rest
xxthunder
xxthunderCOMMUNITY
Explore all skills by this author →
GitHub

naps2-scan

Scan paperwork with OCR via NAPS2.Console.exe and produce ordered PDFs with content-derived filenames.

1|1|Updated Feb 22, 2026
Search Tags:#ocr#pdf#batch processing#document scanning#naps2#filename generation#paperwork digitization
One-click install
npx skills add https://github.com/xxthunder/xxthunder-agentic-skills --skill naps2-scan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: naps2-scan
Source: https://github.com/xxthunder/xxthunder-agentic-skills/tree/main/plugins/xxthunder-paperless-skills/skills/naps2-scan
Command: npx skills add https://github.com/xxthunder/xxthunder-agentic-skills --skill naps2-scan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, and includes scripts (resource) components.

What problem does it solve?

This Skill removes the manual friction of scanning physical paperwork, running OCR, merging pages for simplex double-sided scans, and coming up with a useful filename from the document content.

Core Features & Use Cases

  • End-to-end scan pipeline: runs NAPS2.Console.exe to scan paperwork with OCR enabled, producing a PDF in the working directory.
  • Simplex double-sided support: automatically chains into simplex-merge after a two-pass scan to produce correctly ordered output.
  • Filename proposal with LLM consent: extracts OCR text (after user consent) and proposes a date/sender/topic-based filename, or asks for the details when consent is denied.
  • Batch mode: chains into split-batch to split a scanned stack into one PDF per document, then processes each for naming.

Quick Start

Ask the agent to scan your receipt/letter with OCR, merge if needed, and propose a filename (e.g., “Scan this receipt with NAPS2 and propose the best filename”).

Frequently Asked Questions about naps2-scan

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

FAQPage Schema
How do I automate document scanning with OCR and generate a filename from the content?▼

Automating document scanning with OCR and filename generation is handled by invoking NAPS2.Console.exe with OCR settings, extracting text to propose a date or topic-based filename, and outputting a correctly ordered PDF file.

How do I scan simplex double-sided documents and merge them into one correctly ordered PDF?▼

Scanning simplex double-sided documents requires a two-pass scan that automatically chains into a simplex-merge step, combining the separately scanned fronts and backs into a single correctly ordered PDF file.

Can I split a batch stack of scanned paperwork into individual PDF files?▼

Splitting a batch stack of scanned paperwork into individual PDF files is supported through a batch mode that chains into a split-batch step, processing each separated document individually for naming and output.

Does the filename proposal process require LLM consent for PDF text extraction?▼

PDF text extraction for filename proposal requires explicit LLM consent, ensuring that OCR text is only processed for date, sender, or topic-based naming after the user grants permission or provides the details manually.

What do I need to use NAPS2 for batch processing and paperwork digitization?▼

Using NAPS2 for batch processing and paperwork digitization requires the NAPS2.Console.exe environment and the pypdf dependency for PDF text extraction, enabling end-to-end scanning, OCR, merging, and splitting workflows.

Related Skills

Explore More Software Engineering Skills→
riftzen-bitriftzen-bit

configure-ecc

Install and configure Everything Gemini Code components with verification and optional optimization.

Community
Advanced
ddarkrddarkr
5

oma-pdf

Convert PDF files into structured Markdown with text, tables, headings, and images.

Community
Intermediate
levante-hublevante-hub
39

pdf

Extract text and tables from PDFs using Python libraries.

Official
Intermediate
rjwaltersrjwalters
1

project-photos

Generate deterministic provenance manifests mapping scanned photo captures to published names.

Community
Intermediate