zai-cli

Run vision, web search, page reading, and GitHub code commands via npx zai-cli.

1.0k|105|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/numman-ali/n-skills --skill zai-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: zai-cli
Source: https://github.com/numman-ali/n-skills/tree/main/skills/tools/zai-cli/skills/zai-cli
Command: npx skills add https://github.com/numman-ali/n-skills --skill zai-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Streamline AI task automation by unifying vision, search, page reading, and code operations under one CLI.

Core Features & Use Cases

  • Vision: image and video analysis, OCR, UI-to-code assistance.
  • Search & Reader: real-time web search with domain/recency filtering; web page to Markdown extraction.
  • Repo & Tools: GitHub code search and reading via ZRead; MCP tool discovery and raw calls; TypeScript tool chaining.
  • Use Case: Imagine quickly diagnosing UI issues in a screenshot, then searching the web for fixes, reading docs, and examining related code in a single session.

Quick Start

Export your API key and try basic commands: export Z_AI_API_KEY="your-api-key" npx zai-cli vision analyze ./screenshot.png "What errors do you see?" npx zai-cli search "React 19 new features" --count 5 npx zai-cli read https://docs.example.com/api npx zai-cli repo tree openai/codex --path codex-rs --depth 2

Frequently Asked Questions about zai-cli

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

FAQPage Schema
How do I analyze images and extract text with a CLI tool?

Vision analysis extracts text, identifies objects, and performs OCR on images and videos through command-line commands. ZAI CLI's vision feature analyzes screenshots and media files to diagnose UI issues, extract content, and assist with code generation from visual inputs.

Can I search the web and read documentation from the command line?

Web search and page reading convert live search results and documentation into structured data accessible from your terminal. ZAI CLI performs real-time web searches with domain and recency filtering, then extracts pages to Markdown for immediate analysis in your workflow.

How do I search and explore GitHub repositories without leaving my CLI?

GitHub code exploration lets you query repositories, browse file trees, and read source code directly from the terminal. ZAI CLI's repo commands search and read GitHub code, enabling you to examine dependencies and implementations during development sessions.

What do I need to set up before using a unified CLI for AI tasks?

Setup requires an API key and Node.js to run the CLI via npx. Export your Z_AI_API_KEY environment variable and execute commands immediately without additional dependencies or installation.

Can I chain multiple AI operations—vision, search, and code reading—in one session?

Command chaining unifies separate AI tasks into a single workflow. ZAI CLI supports TypeScript tool chaining and MCP tool discovery, allowing you to diagnose issues in screenshots, search for solutions, read docs, and examine related code sequentially.

What are the limitations of web search and page extraction from a CLI?

Web search respects domain and recency filters but may encounter rate limits or content extraction boundaries on some sites. ZAI CLI's reader converts pages to Markdown; results depend on page structure and JavaScript-rendered content availability.