skills.rest
LuYanFCP
LuYanFCPCOMMUNITY
Explore all skills by this author →
Website𝕏@luyanfcpGitHub

use-ocr

Extract text, tables, formulas, and handwriting from images and PDFs using local OCR tools.

Updated Apr 21, 2026
Search Tags:#ocr#pdf#text extraction#image processing#local processing
One-click install
npx skills add https://github.com/LuYanFCP/common-skills --skill use-ocr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: use-ocr
Source: https://github.com/LuYanFCP/common-skills/tree/main/use-ocr
Command: npx skills add https://github.com/LuYanFCP/common-skills --skill use-ocr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires glmocr[selfhosted], ollama, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for local OCR capabilities, allowing users to extract text, tables, formulas, and handwriting from images and PDFs without relying on cloud APIs.

Core Features & Use Cases

  • Local OCR: Perform OCR tasks locally on macOS using glmocr[selfhosted] and Ollama glm-ocr:latest.
  • Text Extraction: Extract text from images and PDFs.
  • Table Extraction: Extract tables from images and PDFs.
  • Formula Extraction: Extract formulas from images and PDFs.
  • Handwriting Recognition: Recognize handwriting in images and PDFs.
  • Use Case: A user wants to convert a scanned PDF document into editable text without using cloud-based OCR services.

Quick Start

Run python use-ocr/scripts/run_use_ocr.py <input> to extract text from the provided image or PDF.

Frequently Asked Questions about use-ocr

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

FAQPage Schema
How do I extract text from a scanned PDF locally without cloud APIs?▼

To extract text from a scanned PDF locally, you can run the provided Python script `run_use_ocr.py` with your input file. This process uses local OCR tools to digitize documents without relying on external cloud services.

Can I extract tables and formulas from images using local OCR?▼

Yes, local OCR supports extracting tables, formulas, and handwriting from images and PDFs. It processes these elements locally on your machine, enabling structured data extraction directly from scanned documents.

Do I need Ollama and glmocr installed to perform local text recognition?▼

Yes, you must locally install glmocr[selfhosted] and ollama to perform local text recognition. These dependencies provide the underlying OCR processing environment required to execute the extraction scripts.

What is the best way to digitize handwritten notes on macOS?▼

The best way to digitize handwritten notes on macOS is using a local OCR setup with glmocr and ollama. By running the Python extraction script, you can convert handwritten images into editable text locally.

Does local OCR processing handle complex document structures like formulas?▼

Local OCR processing handles complex document structures by extracting formulas, tables, and standard text. It is specifically designed for document digitization tasks that require parsing intricate visual layouts into usable data.

Related Skills

Explore More Product & Management Skills→
unju-aiunju-ai

visa-doc-translate

Translate visa application document images into bilingual English PDFs.

Official
Advanced
moritalousmoritalous
11

pdf

Extract text and tables from PDFs and fill forms using Python libraries.

Community
Advanced
hwj123hwjhwj123hwj
4

paddleocr-doc-parsing

Extract structured Markdown/JSON from PDFs and document images using PaddleOCR.

Community
Advanced
galeepgaleep

liteparse

Extract text and metadata from PDFs, DOCX, and images with spatial bounding boxes.

Community
Advanced