skills.rest
mukaddam-ali
mukaddam-aliCOMMUNITY
Explore all skills by this author β†’
GitHub

VLM

Implement vision-based AI chat for image analysis using the z-ai-web-dev-sdk.

Updated Jul 11, 2026
Search Tags:#typescript#ocr#vision ai#image analysis#image understanding#z-ai-web-dev-sdk#multimodal chat
One-click install
npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill vlm-mukaddam-ali
Or copy as Structured Prompt for Agentβ–Ό
Please help me install this Agent Skill.
Skill: VLM
Source: https://github.com/mukaddam-ali/Anadolu-Kitchen/tree/main/skills/VLM
Command: npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill vlm-mukaddam-ali

SYSTEM DOCUMENTATION & REQUIREMENTS

πŸ’‘ This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve? Building applications that understand images requires wiring up multimodal AI APIs, handling image formats, and managing conversation state. This Skill provides ready-to-use patterns for adding vision chat capabilities to backend applications using the z-ai-web-dev-sdk. ## Core Features & Use Cases - Image Analysis via SDK or CLI: Analyze images from URLs, local files, or base64 data using the createVision API or the z-ai vision CLI command. - Multimodal Content Support: Combine text with images, videos, and documents (image_url, video_url, file_url) in a single message, including multi-image comparisons. - Conversational Vision Sessions: Maintain multi-turn conversations about images with follow-up questions, plus structured outputs for classification, tagging, and OCR text extraction. - Use Case: Build an Express.js endpoint that accepts an image URL and a question, then returns a detailed AI-generated description for e-commerce product analysis or automated alt-text generation. ## Quick Start Ask the AI to analyze an image by running the z-ai vision CLI with a prompt and image URL, or implement a backend endpoint using the createVision example from this Skill.

Frequently Asked Questions about VLM

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze an image with the z-ai-web-dev-sdk?β–Ό

Create a ZAI instance with ZAI.create(), then call zai.chat.completions.createVision with a message containing a text part and an image_url part. The response content is available at response.choices[0].message.content.

How to analyze images from the command line without writing code?β–Ό

Use the z-ai vision CLI command with a prompt and image path, for example: z-ai vision -p "Describe this image" -i "./photo.jpg". It supports multiple images, streaming output, and saving results to a JSON file.

Can I use z-ai-web-dev-sdk in client-side React code?β–Ό

No, the SDK must be used in backend code only. Importing it in client-side code will fail and risks exposing credentials, so always call it from server-side endpoints or API routes.

What image formats does vision chat support?β–Ό

Supported formats include PNG, JPEG, GIF, WebP, and BMP. You can pass images as URLs or as base64-encoded data URIs, with base64 recommended for better performance and reliability.

Can vision chat analyze videos and documents too?β–Ό

Yes, the API supports video_url for video files like MP4 and MOV, and file_url for documents like PDF and DOCX. You can combine multiple content types, such as text with both an image and a document, in one message.

Why is my image analysis returning poor quality results?β–Ό

Poor results usually come from low-quality images or vague prompts. Use high-resolution images, write specific prompts describing exactly what you need, and verify the image URL is publicly accessible.

Related Skills

Explore More Software Engineering Skills→
flaz78flaz78
9

image_base64

Convert images to Base64 strings and reconstruct image files from encoded payloads.

Community
Basic
perceptiv-digitalperceptiv-digital
1

commerce-product-visibility-audit

Classify products as invisible across commerce, search, and feed surfaces using catalog, GMC, GSC, and organic data.

Official
Advanced
jhlee0409jhlee0409

security

Implement OWASP-aligned security controls for API endpoints and user content.

Community
Advanced
framerslabframerslab

vision-ocr

Extract text from images using OCR and AI technology.

Official
Advanced