GLM-OCR Table Recognition

by Z.ai (Zhipu AI)

Apache-2.0

Repository

markdown Document Processing

ocrtable-extractiondocument-processingpdfzhipu-ai

Summary

Extract complex tables, including merged cells and multi-row headers, from images and PDFs into clean Markdown.

Features

Handles merged cells, nested tables, and multi-row headers
Multi-page PDF batch extraction
Clean Markdown table output
Works from local files or remote URLs

Install This Skill

Add this skill to your favorite AI agent in a few steps.

Any AI agent

This skill is plain instructions — it works with any assistant that accepts custom instructions or system prompts.

Copy the skill content with the button below.
Paste it into your agent's instruction file or system prompt (for example AGENTS.md, .cursorrules, or a custom instructions field).
Ask the agent to apply the skill whenever the task matches.

Claude Code & Claude apps

Claude loads skills automatically from its skills directory.

Claude Code

Create a skill folder — personal: ~/.claude/skills/glm-ocr-table-recognition/, or per-project: .claude/skills/glm-ocr-table-recognition/
Save the skill content as SKILL.md inside that folder.
Claude Code picks it up automatically and invokes it when relevant.

mkdir -p ~/.claude/skills/glm-ocr-table-recognition

Claude.ai / Claude Desktop

Enable Skills under Settings → Capabilities, then upload the skill (a folder or zip containing SKILL.md).

One-prompt install

Paste this prompt into any agent with web access and it will install the skill for you.

Install the "GLM-OCR Table Recognition" skill from Onei AI. Fetch https://onei.ai/skills/glm-ocr-table-recognition, extract the full skill content from the page, and save it where you load skills from (for Claude Code: .claude/skills/glm-ocr-table-recognition/SKILL.md). From now on, apply this skill whenever it is relevant to my request.

Skill Content

Markdown Content

Copy this content and use it with your preferred AI agent

# GLM-OCR Table Recognition Skill

Extract tables from images and PDFs and convert them to Markdown format using the ZhiPu GLM-OCR layout parsing API.

## When to Use
- Extract tables from images or scanned documents
- Convert table images to Markdown or Excel format
- Recognize complex tables with merged cells
- Parse financial statements, invoices, reports with tables

## Key Features
- Complex table support: merged cells, nested tables, multi-row headers
- Markdown output: clean, easy to edit and convert
- Multi-page PDF: batch extraction from multi-page PDF documents
- Local file & URL: supports both local files and remote URLs

Setup: script reads the key from the ZHIPU_API_KEY environment variable, reusable across other Zhipu skills.

Description

GLM-OCR Table Recognition is Zhipu AI's official skill for converting table-heavy documents into structured, editable Markdown. It calls the ZhiPu GLM-OCR layout-parsing API to detect and reconstruct tables from images, scanned documents, and multi-page PDFs, specifically handling cases that trip up naive OCR, such as merged cells, nested tables, and multi-row headers.

Input can be a local file or a remote URL, and output is clean Markdown table syntax that is immediately usable downstream or easy for an LLM to reason over further. The skill targets documents where the payoff is in the table rather than the surrounding prose, such as financial statements, invoices, and reports with embedded tabular data, and only needs a Zhipu API key plus Python to run. It is narrower and more focused than a full document-parsing pipeline, so it fits best when the ask is specifically to get a table out of an image or PDF and into something editable, rather than a full structural conversion of a whole document.

Related Skills

Featured

Docling Document Intelligence

by docling-project (IBM)

Parse, convert, chunk, and structurally analyze PDFs, DOCX, PPTX, HTML, and images with IBM's open-source Docling toolkit.

Document Processing

document-processingragpdf

PaddleOCR Document Parsing

by PaddlePaddle

Turn PDFs and scanned images into structured Markdown/JSON: cell-level tables, LaTeX formulas, correct multi-column order.

Document Processing

ocrdocument-processingpdf

Browse all skills →