🎯

glmocr-handwriting

🎯Skill

from zai-org/glm-skills

What it does

Official skills for GLM (Zhipu AI) models, providing multimodal capabilities including image/video captioning, document-based writing, object localization, PDF-to-presentation conversion, and resume screening. Compatible with Claude Code, OpenCode, OpenClaw, and other AI coding agents.

📦

Same repository

zai-org/glm-skills(17 items)

glmocr-handwriting

Installation

Vibe Index InstallInstalls to .claude/skills/

npx vibeindex add zai-org/glm-skills --skill glmocr-handwriting

skills.sh Install⚠ Installs to .agents/skills/

npx skills add zai-org/glm-skills --skill glmocr-handwriting

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/glmocr-handwriting/SKILL.md

SKILL.md

79Installs

AddedApr 13, 2026

View on GitHub Back to Skills

More from this repository10

🎯

glmocr🎯Skill

A skill from the GLM model family that performs general text extraction from images and PDFs, part of the GLM-OCR suite designed for AI coding agents including Claude Code and OpenCode.

🎯

glmv-stock-analyst🎯Skill

A skill from the GLM model family that leverages GLM-V multimodal capabilities to analyze stock charts, financial documents, and market data for investment research and analysis.

🎯

glmv-pdf-to-ppt🎯Skill

A GLM multimodal skill that converts PDF documents into multi-slide HTML presentations, part of the official GLM skills collection designed for AI coding agents including Claude Code and OpenClaw.

🎯

glm-image-gen🎯Skill

Official skills for the GLM family of models, designed for multiple agent architectures including Claude Code and OpenClaw. Provides multimodal skills for image captioning, document-based writing, object localization, PDF conversion, and resume screening.

🎯

glmocr-formula🎯Skill

An official GLM-OCR skill that extracts mathematical formulas from images and documents into LaTeX format, part of the GLM skills collection designed for agent architectures including Claude Code, OpenCode, and other AI coding agents.

🎯

glmv-grounding🎯Skill

Official skill collection for the GLM family of models, covering multimodal vision (captioning, object grounding, document-to-presentation), OCR (text, formulas, handwriting, tables), and image generation. Compatible with Claude Code, OpenCode, OpenClaw, and other AI coding agents.

🎯

glmv-web-replication🎯Skill

An official GLM skill that uses multimodal (GLM-V) capabilities to create frontend visual replicas of existing websites, designed for AI coding agents including Claude Code and OpenCode.

🎯

glmv-caption🎯Skill

A multimodal captioning skill from GLM Skills that generates captions and descriptions for images, videos, and documents using GLM-V models. Part of a unified skill collection designed for Claude Code, OpenCode, OpenClaw, and other AI coding agents.

🎯

glmocr-table🎯Skill

Official skills for the GLM family of models, providing multimodal capabilities like image captioning, object localization, PDF-to-presentation conversion, resume screening, and stock analysis for AI coding agents including Claude Code and OpenCode.

🎯

glmv-prd-to-app🎯Skill

A skill from the official GLM model family collection that converts product requirement documents into applications, part of a unified set of skills for multimodal, code, and web agent capabilities across Claude Code and other AI coding agents.