---
title: "GLM-OCR Text Extraction Skill - Air Market"
description: "Sometimes the text you need is stuck inside a picture or a PDF and you cannot copy it. Point this at the file and it reads the text back out. It handles tables, mathematical formulas, and handwriting…"
canonical: "https://airmarket.ai/app/glmocr"
---

[Air Market](/) / [Data & Analytics](/category/data) / GLM-OCR Text Extraction Skill

Skill by [Z.ai](/@zai-org)

# GLM-OCR Text Extraction Skill

Pull the words out of a photo, a scan, or a PDF

## What this does

Sometimes the text you need is stuck inside a picture or a PDF and you cannot copy it. Point this at the file and it reads the text back out. It handles tables, mathematical formulas, and handwriting as well as ordinary printed type.

### Top 3 things it does for you

- Get the text out of a screenshot or photo
- Turn a scanned document into text
- Read a table out of an image

## Information

**GLM-OCR Text Extraction Skill at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [Z.ai](/@zai-org) |
| Category | [Data & Analytics](/category/data) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Size | 28 KB |
| Licence | Apache-2.0 |
| Repository | [zai-org/GLM-OCR](https://github.com/zai-org/GLM-OCR/tree/cef4d0ea120d1741f5cefe8985eee45f6c8eff1d/skills/glmocr) |
| GitHub stars | 7,354 (as of Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of GLM-OCR Text Extraction Skill and flagged nothing. AIR's verdict: **safe**.

**What GLM-OCR Text Extraction Skill's check was run against**

|  |  |
| --- | --- |
| Commit | cef4d0ea120d1741f5cefe8985eee45f6c8eff1d |
| Content hash | 7b4870366d80a8c3956b98459dc8e22e07327dfa037ab5093ea004050e8c16b1 |
| Files read | [Browse the files at this exact commit](https://github.com/zai-org/GLM-OCR/blob/cef4d0ea120d1741f5cefe8985eee45f6c8eff1d/skills/glmocr/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for GLM-OCR Text Extraction Skill](/security/glmocr)

## About GLM-OCR Text Extraction Skill

This reads text out of images and PDFs using the GLM-OCR API. Beyond plain printed text, it covers table recognition, formula extraction, and handwriting.

Use it any time the content you want is trapped in a picture: extracting text from an image, scanning a document, converting pictures to text, or processing image files to get at what they say.

## What's inside

- SKILL.md - instructions
- references/output_schema.md - reference
- scripts/config_setup.py - script
- scripts/glm_ocr_cli.py - script
- scripts/requirements.txt - reference

## Questions

### Is GLM-OCR Text Extraction Skill safe to install?

AIR scanned this exact version of GLM-OCR Text Extraction Skill and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit cef4d0ea120d, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/glmocr.

### How do I install GLM-OCR Text Extraction Skill?

Open https://airmarket.ai/app/glmocr on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/zai-org/GLM-OCR/tree/cef4d0ea120d1741f5cefe8985eee45f6c8eff1d/skills/glmocr. Install from that link, not the branch.

## Related on Air Market

- [More Data & Analytics listings](/category/data)
- [Everything by Z.ai](/@zai-org)

---

Canonical URL: <https://airmarket.ai/app/glmocr>