Home Projects GLM-skills
GLM-skills
Python

GLM-skills

Official skills for the GLM family of models.

by zai-org · GitHub
Stars
Forks
Trending
License
Created
Last commit
Category
Language
glmmultimodalocrApache-2.0Python
View on GitHub
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
GLM-skills — GitHub preview card
📈 Star history
468452
2026-07-202026-08-31
📈 Track GLM-skills

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Official skills for the GLM family of models.

GLM-skills has 468 stars on GitHub. It has been forked 41 times. GLM-skills is written mainly in Python. It has been in active development since 2026. GLM-skills is available under the Apache-2.0 license. Its main topics are glm, multimodal, ocr, skills.

Frequently asked questions

What is GLM-skills?

Official skills for the GLM family of models.

Is GLM-skills open source?

GLM-skills is an open-source project. It is released under the Apache-2.0 license.

Is GLM-skills free?

Yes. GLM-skills is free and open source — you can use, modify and self-host it.

What license does GLM-skills use?

GLM-skills is available under the Apache-2.0 license.

What language is GLM-skills written in?

GLM-skills is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — GLM-skills

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=zai-org-glm-skills)](https://olud.ai/project/zai-org-glm-skills.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
dsh-vision-complete
给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件:看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读,一键安装(DSH 插件)。
42 · dashscope
sharesvisionocr
dsh-vision-router
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level v…
1k · deepseek-harness
sharesvisionmultimodal
dsh-vision
Near-native image understanding for DeepSeek Harness
88 · deepseek-harness
sharesvisionmultimodal
agent-vision-toolkit
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit…
1.1k · agent
sharesvisionglm
caffe
Caffe: a fast open framework for deep learning.
34.6k · deep-learning
sharesvision
chandra
OCR model that handles complex tables, forms, handwriting with full layout.
11.6k · ai
sharesocr
claude-code-vision-skill
为 Claude Code 赋能多模态视觉能力,适配 纯文本 LLM 底座,用于截图 / UI / 图表分析;搭配 browser-harness 可做前端布局自动化检查。
171 · agent-skills
sharesvisionmultimodal
modlens
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding…
3.8k · agent-skills
sharesvisionglm
ocrs
Rust library and CLI tool for OCR (extracting text from images)
1.9k · computer-vision
sharesocr
PixelRAG
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-nativ…
9.8k · agent
sharesvisionmultimodal

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.