full-aigc-skills/zhipu-skills · Archived
zhipu-ocr
使用智谱 GLM-4V-Flash 视觉模型识别图片中的文字。支持 JPG/PNG/GIF/BMP/WebP 等常见图片格式,单张识别和批量处理。当用户发送图片并要求识别文字、提取文字或 OCR 时触发。来源: https://github.com/Wcowin/zhipu-OCR-skill (MIT)
Installation
npx skills add https://github.com/full-aigc-skills/zhipu-skills
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
智谱 AI 视频生成模型选型与调用指南。涵盖 CogVideoX-3、Vidu 2、Vidu Q1 及免费的 CogVideoX-Flash…
1 installs智谱 AI 图像生成模型选型与调用指南。涵盖 CogView-4、GLM-Image 及免费的 CogView-3-Flash。当用户…
1 installs智谱 AI 语音模型选型与调用指南。涵盖文本转语音 (TTS)、声音克隆、语音识别 (ASR)、端到端语音对话…
1 installs智谱 AI 视觉语言模型 (VLM) 选型与调用指南。涵盖 GLM-4.6V、GLM-4.1V-Thinking、GLM-OCR、AutoGLM-P…
1 installsAlso in this package
Other skills from full-aigc-skills/zhipu-skills.
npx skills add https://github.com/full-aigc-skills/zhipu-skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
History
- First recorded snapshot · 1 installs