glmocr-table

Name: glmocr-table
Availability: InStock
Author: Almaz

Extract tables from images and PDFs into Markdown using the GLM-OCR layout parsing API.

Updated Mar 25, 2026

Search Tags:#ocr #pdf #markdown #image #table-extraction #glm-ocr

Ready to run

npx skills add https://github.com/almazom/agents_slash_skills --skill glmocr-table-almazom

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: glmocr-table
Source: https://github.com/almazom/agents_slash_skills/tree/main/glmocr-table
Command: npx skills add https://github.com/almazom/agents_slash_skills --skill glmocr-table-almazom

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Efficiently extract tables from images and PDFs and convert them into clean Markdown tables, including complex layouts with merged cells and multi-page documents.

Core Features & Use Cases

Complex table support with merged cells, nested tables, and multi-page documents
Markdown output that's easy to edit and integrate into documents
Works with local files or remote URLs; handles multi-page PDFs and image/table OCR
Use cases include parsing financial reports, invoices, and spreadsheets

Quick Start

Provide an image or PDF to the GLM-OCR API via the CLI to obtain a Markdown table.

Frequently Asked Questions about glmocr-table

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

FAQPage Schema

How do I extract tables from a scanned PDF and output them as Markdown?▼

To extract tables from a scanned PDF and output Markdown, provide the file to the GLM-OCR layout parsing API via the CLI. It processes multi-page documents and returns clean Markdown tables for editing and analysis.

Can I convert images with complex table layouts into Markdown?▼

Yes, you can convert images with complex table layouts into Markdown. The API handles merged cells and nested tables, transforming tabular image data into structured Markdown output.

Do I need an API key to parse PDF tables using GLM-OCR?▼

Yes, you need the ZHIPU_API_KEY environment variable to parse PDF tables. The Skill requires this key to authenticate requests to the fixed layout parsing endpoint at open.bigmodel.cn.

Does table extraction from PDFs work with remote URLs or only local files?▼

Table extraction from PDFs works with both local files and remote URLs. You can pass either source to the CLI script to retrieve raw results or converted Markdown tables from the layout parsing API.

What is the best way to convert financial reports and invoices into editable tables?▼

The best way to convert financial reports and invoices into editable tables is using OCR layout parsing. It extracts tabular data from multi-page PDFs and images, outputting clean Markdown tables for reporting.