glmocr-handwriting
Installation
SKILL.md
GLM-OCR Handwriting Recognition Skill / GLM-OCR 手写体识别技能
Recognize handwritten text from images and PDFs using the ZhiPu GLM-OCR layout parsing API.
When to Use / 使用场景
- Extract text from handwritten notes, letters, or documents / 从手写笔记、信件或文档中提取文字
- Convert handwriting to editable text / 将手写内容转为可编辑文本
- Recognize mixed handwritten and printed content / 识别手写和印刷混排内容
- Read handwritten formulas, labels, or annotations / 读取手写公式、标签或批注
- User mentions "handwriting OCR", "recognize handwriting", "手写识别", "手写体OCR", "识别手写字"
Key Features / 核心特性
- Multi-style support: Handles various handwriting styles including cursive and print
- Multi-language: Supports Chinese, English, and mixed-language handwriting
- Mixed content: Can recognize documents with both handwritten and printed text
- Local file & URL: Supports both local files and remote URLs
Related skills
More from zai-org/glm-skills
glmv-pdf-to-ppt
Convert a PDF (research paper, report, or any document) into a polished multi-slide
26glmv-stock-analyst
>
26glm-image-gen
Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API.
24glm-master-skill
|
24glmv-grounding
>
23glmv-caption
Generate captions (descriptions) for images, videos, and documents using ZhiPu
22