Analyze images with the GLM-4.6V multimodal model for description and OCR.
npx skills add https://github.com/BoChao1Zhang/dotfiles --skill glm-vision-bochao1zhang
Please help me install this Agent Skill. Skill: glm-vision Source: https://github.com/BoChao1Zhang/dotfiles/tree/main/dot_claude/skills/glm-vision Command: npx skills add https://github.com/BoChao1Zhang/dotfiles --skill glm-vision-bochao1zhang
Analyzes images using the GLM-4.6V multimodal model to understand visual content, extract text (OCR), and interpret scenes.
Provide an image to analyze by attaching it to a prompt, after setting ZHIPU_API_KEY in your environment.
High-intent search queries and answers about installing and using this skill.
This Skill performs OCR text extraction by analyzing images with the GLM-4.6V multimodal model. You simply provide an image_url or local image input within your prompt to extract and interpret the embedded text.
Yes, you can perform image analysis using an OpenAI compatible client by configuring the base_url to https://open.bigmodel.cn/api/paas/v4. You also need to set your ZHIPU_API_KEY in the environment to authenticate the requests.
Yes, multimodal video understanding supports multi-image comparison alongside scene interpretation. The GLM-4.6V model processes multiple images or video frames to recognize objects and compare visual content based on your prompt.
The best way to describe image content automatically is by triggering the GLM-4.6V model with a prompt like "请描述这张图片". The model analyzes the visual elements and generates a detailed description of the scene.
Yes, you need a ZHIPU_API_KEY to run object recognition tasks. The key authenticates your requests to the GLM-4.6V multimodal model via the OpenAI compatible client, enabling scene element analysis and object recognition.
black-ytConfigure and debug an OpenAI-compatible context overlay proxy with YAML rules.
smallnestConvert PDFs, Word, Excel, HTML, and images with OCR into Markdown.
jrajasekeraStandardize access to Z.ai GLM chat, vision, media, and retrieval APIs.
nexscope-aiAnalyze image URLs with multimodal AI for visual content and OCR.
